diff --git "a/profile_trace/iteration_12288/rank4_trace.json" "b/profile_trace/iteration_12288/rank4_trace.json" new file mode 100644--- /dev/null +++ "b/profile_trace/iteration_12288/rank4_trace.json" @@ -0,0 +1,68515 @@ + +{ + "schemaVersion": 1, + "deviceProperties": [ + { + "id": 0, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 1, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 2, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 3, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 4, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 5, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 6, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 7, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + } + ], + "cupti_version": 22, + "cuda_runtime_version": 12040, + "cuda_driver_version": 12080, + "distributedInfo": {"backend": "nccl", "rank": 4, "world_size": 8, "pg_count": 1, "pg_config": [{"pg_name": "0", "pg_desc": "default_pg", "backend_config": "cuda:nccl", "pg_size": 8, "ranks": [0, 1, 2, 3, 4, 5, 6, 7]}], "nccl_version": "2.21.5"}, + "record_shapes": 1, + "trace_id": "6A48D436CA934FD08149E99EC7D2FEF3", + "traceEvents": [ + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: DivBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115506459.684, "dur": 119.312, + "args": { + "External id": 229889,"Record function id": 0, "Sequence number": 2757958, "Fwd thread id": 1, "Ev Idx": 0 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "DivBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115506477.242, "dur": 92.542, + "args": { + "External id": 229890,"Sequence number": 2757958, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 1 + } + }, + { + "ph": "f", "id": 1, "pid": 4183440, "tid": 31337, "ts": 667115506477.242, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 4183440, "tid": 31337, + "ts": 667115506484.855, "dur": 82.881, + "args": { + "External id": 229891,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 2 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115506592.058, "dur": 239.595, + "args": { + "External id": 229892,"Record function id": 0, "Ev Idx": 3 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward", "pid": 4183440, "tid": 31337, + "ts": 667115506643.479, "dur": 116.852, + "args": { + "External id": 229893,"Record function id": 0, "Ev Idx": 4 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.19", "pid": 4183440, "tid": 31337, + "ts": 667115506703.713, "dur": 45.831, + "args": { + "External id": 229894,"Record function id": 0, "Ev Idx": 5 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115506765.380, "dur": 2.187, + "args": { + "External id": 229895,"Sequence number": 2757957, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 6 + } + }, + { + "ph": "f", "id": 2, "pid": 4183440, "tid": 31337, "ts": 667115506765.380, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 31337, + "ts": 667115506771.437, "dur": 55.227, + "args": { + "External id": 229896,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 7 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 31337, + "ts": 667115506778.240, "dur": 47.930, + "args": { + "External id": 229897,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 8 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115506789.457, "dur": 3.440, + "args": { + "External id": 229898,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115506841.840, "dur": 16754.008, + "args": { + "External id": 229899,"Record function id": 0, "Sequence number": 2757955, "Fwd thread id": 1, "Ev Idx": 10 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115506843.537, "dur": 16742.156, + "args": { + "External id": 229900,"Sequence number": 2757955, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11 + } + }, + { + "ph": "f", "id": 3, "pid": 4183440, "tid": 31337, "ts": 667115506843.537, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115506883.792, "dur": 3.805, + "args": { + "External id": 229901,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115506892.656, "dur": 16574.853, + "args": { + "External id": 229902,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115506894.452, "dur": 16572.724, + "args": { + "External id": 229903,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 14 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115506900.299, "dur": 6.588, + "args": { + "External id": 229904,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115506908.679, "dur": 16557.093, + "args": { + "External id": 229905,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 16 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 4183440, "tid": 31337, + "ts": 667115523471.963, "dur": 0.598, + "args": { + "External id": 229906,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 17 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 4183440, "tid": 31337, + "ts": 667115523474.362, "dur": 3.084, + "args": { + "External id": 229907,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 18 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 4183440, "tid": 31337, + "ts": 667115523475.948, "dur": 1.133, + "args": { + "External id": 229908,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 19 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 4183440, "tid": 31337, + "ts": 667115523483.765, "dur": 40.114, + "args": { + "External id": 229909,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 20 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 4183440, "tid": 31337, + "ts": 667115523532.936, "dur": 43.497, + "args": { + "External id": 229910,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 4183440, "tid": 31337, + "ts": 667115523534.513, "dur": 41.734, + "args": { + "External id": 229911,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 22 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 4183440, "tid": 31337, + "ts": 667115523536.311, "dur": 39.630, + "args": { + "External id": 229912,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 23 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115523606.861, "dur": 17.224, + "args": { + "External id": 229913,"Record function id": 0, "Sequence number": 2757954, "Fwd thread id": 1, "Ev Idx": 24 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115523608.637, "dur": 12.965, + "args": { + "External id": 229914,"Sequence number": 2757954, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 25 + } + }, + { + "ph": "f", "id": 4, "pid": 4183440, "tid": 31337, "ts": 667115523608.637, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115523611.882, "dur": 9.491, + "args": { + "External id": 229915,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 26 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115523615.254, "dur": 5.942, + "args": { + "External id": 229916,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 27 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115523629.354, "dur": 114.373, + "args": { + "External id": 229917,"Record function id": 0, "Sequence number": 2757953, "Fwd thread id": 1, "Ev Idx": 28 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115523630.533, "dur": 104.583, + "args": { + "External id": 229918,"Sequence number": 2757953, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 29 + } + }, + { + "ph": "f", "id": 5, "pid": 4183440, "tid": 31337, "ts": 667115523630.533, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183440, "tid": 31337, + "ts": 667115523633.888, "dur": 100.629, + "args": { + "External id": 229919,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], [], [], []], "Ev Idx": 30 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 31337, + "ts": 667115523639.158, "dur": 56.570, + "args": { + "External id": 229920,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 1024]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 31 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115523642.708, "dur": 5.340, + "args": { + "External id": 229921,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 1024]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 32 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 31337, + "ts": 667115523649.338, "dur": 46.104, + "args": { + "External id": 229922,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 33 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 31337, + "ts": 667115523676.142, "dur": 18.597, + "args": { + "External id": 229923,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 34 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115523700.455, "dur": 5.062, + "args": { + "External id": 229924,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], [], []], "Ev Idx": 35 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115523703.542, "dur": 1.560, + "args": { + "External id": 229925,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[4194304, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4194304, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], []], "Ev Idx": 36 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115523706.786, "dur": 26.562, + "args": { + "External id": 229926,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 37 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115523749.542, "dur": 64.461, + "args": { + "External id": 229927,"Record function id": 0, "Sequence number": 2757952, "Fwd thread id": 1, "Ev Idx": 38 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115523750.648, "dur": 59.711, + "args": { + "External id": 229928,"Sequence number": 2757952, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 39 + } + }, + { + "ph": "f", "id": 6, "pid": 4183440, "tid": 31337, "ts": 667115523750.648, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 4183440, "tid": 31337, + "ts": 667115523755.039, "dur": 55.057, + "args": { + "External id": 229929,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "2", "3"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], []], "Ev Idx": 40 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 31337, + "ts": 667115523759.151, "dur": 22.221, + "args": { + "External id": 229930,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 41 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115523762.198, "dur": 3.181, + "args": { + "External id": 229931,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 42 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 31337, + "ts": 667115523766.286, "dur": 14.783, + "args": { + "External id": 229932,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 43 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 31337, + "ts": 667115523769.126, "dur": 11.481, + "args": { + "External id": 229933,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], []], "Ev Idx": 44 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183440, "tid": 31337, + "ts": 667115523784.937, "dur": 5.402, + "args": { + "External id": 229934,"Record function id": 0, "Concrete Inputs": ["", "2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], []], "Input Dims": [[16, 4096, 4, 1024], [], []], "Ev Idx": 45 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115523788.694, "dur": 0.949, + "args": { + "External id": 229935,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[16777216, 4096, 1]", "3072"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 46 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115523791.133, "dur": 18.394, + "args": { + "External id": 229936,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 47 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115523817.924, "dur": 99.088, + "args": { + "External id": 229937,"Record function id": 0, "Sequence number": 2757951, "Fwd thread id": 1, "Ev Idx": 48 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115523819.165, "dur": 94.398, + "args": { + "External id": 229938,"Sequence number": 2757951, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 49 + } + }, + { + "ph": "f", "id": 7, "pid": 4183440, "tid": 31337, "ts": 667115523819.165, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183440, "tid": 31337, + "ts": 667115523820.745, "dur": 92.455, + "args": { + "External id": 229939,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], [], []], "Ev Idx": 50 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 31337, + "ts": 667115523825.539, "dur": 18.170, + "args": { + "External id": 229940,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 51 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115523826.690, "dur": 2.094, + "args": { + "External id": 229941,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 52 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 31337, + "ts": 667115523829.579, "dur": 13.858, + "args": { + "External id": 229942,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 53 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 31337, + "ts": 667115523830.489, "dur": 12.579, + "args": { + "External id": 229943,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], []], "Ev Idx": 54 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115523846.324, "dur": 4.033, + "args": { + "External id": 229944,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], []], "Ev Idx": 55 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115523847.537, "dur": 2.639, + "args": { + "External id": 229945,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "[16777216, 4096, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 56 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115523851.289, "dur": 61.240, + "args": { + "External id": 229946,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], [16, 4096, 4, 1024], []], "Ev Idx": 57 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115523920.552, "dur": 68.104, + "args": { + "External id": 229947,"Record function id": 0, "Sequence number": 2757950, "Fwd thread id": 1, "Ev Idx": 58 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115523921.486, "dur": 64.002, + "args": { + "External id": 229948,"Sequence number": 2757950, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 59 + } + }, + { + "ph": "f", "id": 8, "pid": 4183440, "tid": 31337, "ts": 667115523921.486, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183440, "tid": 31337, + "ts": 667115523922.753, "dur": 62.419, + "args": { + "External id": 229949,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], [], []], "Ev Idx": 60 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 31337, + "ts": 667115523923.513, "dur": 17.020, + "args": { + "External id": 229950,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 61 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115523925.989, "dur": 2.013, + "args": { + "External id": 229951,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 62 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 31337, + "ts": 667115523928.585, "dur": 11.701, + "args": { + "External id": 229952,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 63 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 31337, + "ts": 667115523929.361, "dur": 10.604, + "args": { + "External id": 229953,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], []], "Ev Idx": 64 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115523941.292, "dur": 4.204, + "args": { + "External id": 229954,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], []], "Ev Idx": 65 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115523944.509, "dur": 0.825, + "args": { + "External id": 229955,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "[16777216, 4096, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 66 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115523947.953, "dur": 36.632, + "args": { + "External id": 229956,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], [16, 4096, 4, 1024], []], "Ev Idx": 67 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115523992.609, "dur": 35.164, + "args": { + "External id": 229957,"Record function id": 0, "Sequence number": 2757949, "Fwd thread id": 1, "Ev Idx": 68 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115523993.591, "dur": 0.922, + "args": { + "External id": 229958,"Sequence number": 2757949, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 69 + } + }, + { + "ph": "f", "id": 9, "pid": 4183440, "tid": 31337, "ts": 667115523993.591, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 31337, + "ts": 667115523996.913, "dur": 27.644, + "args": { + "External id": 229959,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 70 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 31337, + "ts": 667115523998.879, "dur": 25.215, + "args": { + "External id": 229960,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 71 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115524003.282, "dur": 2.273, + "args": { + "External id": 229961,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 72 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115524032.800, "dur": 1086.556, + "args": { + "External id": 229962,"Record function id": 0, "Sequence number": 2757947, "Fwd thread id": 1, "Ev Idx": 73 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115524034.155, "dur": 1053.838, + "args": { + "External id": 229963,"Sequence number": 2757947, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 74 + } + }, + { + "ph": "f", "id": 10, "pid": 4183440, "tid": 31337, "ts": 667115524034.155, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115524067.646, "dur": 2.248, + "args": { + "External id": 229964,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 75 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115524072.316, "dur": 928.307, + "args": { + "External id": 229965,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 76 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115524073.538, "dur": 926.849, + "args": { + "External id": 229966,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 77 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115524076.008, "dur": 4.709, + "args": { + "External id": 229967,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 78 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115524081.407, "dur": 918.013, + "args": { + "External id": 229968,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 79 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 4183440, "tid": 31337, + "ts": 667115525003.791, "dur": 0.466, + "args": { + "External id": 229969,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 80 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 4183440, "tid": 31337, + "ts": 667115525005.764, "dur": 4.286, + "args": { + "External id": 229970,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 81 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 4183440, "tid": 31337, + "ts": 667115525008.535, "dur": 1.096, + "args": { + "External id": 229971,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 82 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 4183440, "tid": 31337, + "ts": 667115525013.942, "dur": 22.140, + "args": { + "External id": 229972,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 83 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 4183440, "tid": 31337, + "ts": 667115525041.047, "dur": 40.157, + "args": { + "External id": 229973,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 84 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 4183440, "tid": 31337, + "ts": 667115525042.210, "dur": 38.801, + "args": { + "External id": 229974,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 85 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 4183440, "tid": 31337, + "ts": 667115525043.155, "dur": 37.556, + "args": { + "External id": 229975,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 86 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 31337, + "ts": 667115525096.631, "dur": 19.365, + "args": { + "External id": 229976,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 87 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115525126.626, "dur": 15.205, + "args": { + "External id": 229977,"Record function id": 0, "Sequence number": 2757946, "Fwd thread id": 1, "Ev Idx": 88 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115525128.068, "dur": 11.564, + "args": { + "External id": 229978,"Sequence number": 2757946, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 89 + } + }, + { + "ph": "f", "id": 11, "pid": 4183440, "tid": 31337, "ts": 667115525128.068, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115525132.386, "dur": 7.010, + "args": { + "External id": 229979,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 90 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115525135.737, "dur": 3.493, + "args": { + "External id": 229980,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 91 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115525145.215, "dur": 59.631, + "args": { + "External id": 229981,"Record function id": 0, "Sequence number": 2757945, "Fwd thread id": 1, "Ev Idx": 92 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115525146.125, "dur": 54.711, + "args": { + "External id": 229982,"Sequence number": 2757945, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 93 + } + }, + { + "ph": "f", "id": 12, "pid": 4183440, "tid": 31337, "ts": 667115525146.125, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183440, "tid": 31337, + "ts": 667115525147.907, "dur": 52.621, + "args": { + "External id": 229983,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], [], [], []], "Ev Idx": 94 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 31337, + "ts": 667115525149.924, "dur": 23.634, + "args": { + "External id": 229984,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 1024]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 95 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115525152.951, "dur": 4.292, + "args": { + "External id": 229985,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 1024]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 96 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 31337, + "ts": 667115525158.190, "dur": 15.110, + "args": { + "External id": 229986,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 97 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 31337, + "ts": 667115525159.475, "dur": 13.414, + "args": { + "External id": 229987,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 98 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115525175.142, "dur": 2.731, + "args": { + "External id": 229988,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], [], []], "Ev Idx": 99 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115525176.799, "dur": 0.887, + "args": { + "External id": 229989,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[4194304, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4194304, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], []], "Ev Idx": 100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115525178.989, "dur": 20.819, + "args": { + "External id": 229990,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115525210.733, "dur": 55.979, + "args": { + "External id": 229991,"Record function id": 0, "Sequence number": 2757944, "Fwd thread id": 1, "Ev Idx": 102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115525211.745, "dur": 52.422, + "args": { + "External id": 229992,"Sequence number": 2757944, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 103 + } + }, + { + "ph": "f", "id": 13, "pid": 4183440, "tid": 31337, "ts": 667115525211.745, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 4183440, "tid": 31337, + "ts": 667115525214.799, "dur": 49.079, + "args": { + "External id": 229993,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "2", "2"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], []], "Ev Idx": 104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 31337, + "ts": 667115525216.315, "dur": 18.662, + "args": { + "External id": 229994,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115525217.050, "dur": 2.789, + "args": { + "External id": 229995,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 31337, + "ts": 667115525220.443, "dur": 14.260, + "args": { + "External id": 229996,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 31337, + "ts": 667115525221.166, "dur": 13.195, + "args": { + "External id": 229997,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], []], "Ev Idx": 108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183440, "tid": 31337, + "ts": 667115525236.271, "dur": 5.777, + "args": { + "External id": 229998,"Record function id": 0, "Concrete Inputs": ["", "2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], []], "Input Dims": [[16, 4096, 4, 1024], [], []], "Ev Idx": 109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115525240.799, "dur": 0.753, + "args": { + "External id": 229999,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[16777216, 4096, 1]", "2048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115525242.906, "dur": 20.310, + "args": { + "External id": 230000,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115525271.801, "dur": 90.628, + "args": { + "External id": 230001,"Record function id": 0, "Sequence number": 2757943, "Fwd thread id": 1, "Ev Idx": 112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115525272.914, "dur": 86.837, + "args": { + "External id": 230002,"Sequence number": 2757943, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 113 + } + }, + { + "ph": "f", "id": 14, "pid": 4183440, "tid": 31337, "ts": 667115525272.914, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183440, "tid": 31337, + "ts": 667115525275.566, "dur": 83.759, + "args": { + "External id": 230003,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], [], []], "Ev Idx": 114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 31337, + "ts": 667115525276.614, "dur": 17.347, + "args": { + "External id": 230004,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115525277.511, "dur": 2.287, + "args": { + "External id": 230005,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 31337, + "ts": 667115525280.579, "dur": 13.138, + "args": { + "External id": 230006,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 31337, + "ts": 667115525281.427, "dur": 11.928, + "args": { + "External id": 230007,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], []], "Ev Idx": 118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115525294.924, "dur": 3.930, + "args": { + "External id": 230008,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], []], "Ev Idx": 119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115525298.053, "dur": 0.669, + "args": { + "External id": 230009,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "[16777216, 4096, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115525299.438, "dur": 59.034, + "args": { + "External id": 230010,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], [16, 4096, 4, 1024], []], "Ev Idx": 121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115525367.888, "dur": 77.751, + "args": { + "External id": 230011,"Record function id": 0, "Sequence number": 2757942, "Fwd thread id": 1, "Ev Idx": 122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115525369.093, "dur": 59.557, + "args": { + "External id": 230012,"Sequence number": 2757942, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 123 + } + }, + { + "ph": "f", "id": 15, "pid": 4183440, "tid": 31337, "ts": 667115525369.093, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183440, "tid": 31337, + "ts": 667115525372.057, "dur": 56.306, + "args": { + "External id": 230013,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], [], []], "Ev Idx": 124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 31337, + "ts": 667115525372.947, "dur": 15.183, + "args": { + "External id": 230014,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115525373.482, "dur": 1.702, + "args": { + "External id": 230015,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 31337, + "ts": 667115525375.793, "dur": 12.092, + "args": { + "External id": 230016,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 31337, + "ts": 667115525376.486, "dur": 11.078, + "args": { + "External id": 230017,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], []], "Ev Idx": 128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115525389.364, "dur": 1.696, + "args": { + "External id": 230018,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], []], "Ev Idx": 129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115525390.219, "dur": 0.706, + "args": { + "External id": 230019,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "[16777216, 4096, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115525391.643, "dur": 36.108, + "args": { + "External id": 230020,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], [16, 4096, 4, 1024], []], "Ev Idx": 131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 31337, + "ts": 667115525431.808, "dur": 12.560, + "args": { + "External id": 230021,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], [16, 4096, 4, 1024], []], "Ev Idx": 132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115525449.454, "dur": 35.018, + "args": { + "External id": 230022,"Record function id": 0, "Sequence number": 2757941, "Fwd thread id": 1, "Ev Idx": 133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115525452.533, "dur": 0.834, + "args": { + "External id": 230023,"Sequence number": 2757941, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 134 + } + }, + { + "ph": "f", "id": 16, "pid": 4183440, "tid": 31337, "ts": 667115525452.533, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 31337, + "ts": 667115525455.646, "dur": 26.057, + "args": { + "External id": 230024,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 31337, + "ts": 667115525457.218, "dur": 23.888, + "args": { + "External id": 230025,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115525463.988, "dur": 0.444, + "args": { + "External id": 230026,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115525488.567, "dur": 1472.134, + "args": { + "External id": 230027,"Record function id": 0, "Sequence number": 2757939, "Fwd thread id": 1, "Ev Idx": 138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115525503.915, "dur": 1430.892, + "args": { + "External id": 230028,"Sequence number": 2757939, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 139 + } + }, + { + "ph": "f", "id": 17, "pid": 4183440, "tid": 31337, "ts": 667115525503.915, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115525530.153, "dur": 2.429, + "args": { + "External id": 230029,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115525534.652, "dur": 1318.711, + "args": { + "External id": 230030,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115525535.919, "dur": 1317.204, + "args": { + "External id": 230031,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115525538.172, "dur": 3.271, + "args": { + "External id": 230032,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115525542.299, "dur": 1309.953, + "args": { + "External id": 230033,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 4183440, "tid": 31337, + "ts": 667115526856.029, "dur": 0.265, + "args": { + "External id": 230034,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 4183440, "tid": 31337, + "ts": 667115526857.511, "dur": 2.150, + "args": { + "External id": 230035,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 4183440, "tid": 31337, + "ts": 667115526858.725, "dur": 0.815, + "args": { + "External id": 230036,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 4183440, "tid": 31337, + "ts": 667115526863.344, "dur": 19.940, + "args": { + "External id": 230037,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 4183440, "tid": 31337, + "ts": 667115526889.565, "dur": 38.422, + "args": { + "External id": 230038,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 4183440, "tid": 31337, + "ts": 667115526890.683, "dur": 37.095, + "args": { + "External id": 230039,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 4183440, "tid": 31337, + "ts": 667115526893.020, "dur": 34.479, + "args": { + "External id": 230040,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 31337, + "ts": 667115526941.727, "dur": 15.966, + "args": { + "External id": 230041,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115526967.842, "dur": 9.482, + "args": { + "External id": 230042,"Record function id": 0, "Sequence number": 2757938, "Fwd thread id": 1, "Ev Idx": 153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115526969.335, "dur": 6.116, + "args": { + "External id": 230043,"Sequence number": 2757938, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 154 + } + }, + { + "ph": "f", "id": 18, "pid": 4183440, "tid": 31337, "ts": 667115526969.335, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115526971.319, "dur": 3.919, + "args": { + "External id": 230044,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115526972.503, "dur": 2.597, + "args": { + "External id": 230045,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115526980.535, "dur": 60.227, + "args": { + "External id": 230046,"Record function id": 0, "Sequence number": 2757937, "Fwd thread id": 1, "Ev Idx": 157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115526981.242, "dur": 55.328, + "args": { + "External id": 230047,"Sequence number": 2757937, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 158 + } + }, + { + "ph": "f", "id": 19, "pid": 4183440, "tid": 31337, "ts": 667115526981.242, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183440, "tid": 31337, + "ts": 667115526982.774, "dur": 53.336, + "args": { + "External id": 230048,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], [], [], []], "Ev Idx": 159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 31337, + "ts": 667115526988.073, "dur": 19.971, + "args": { + "External id": 230049,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 1024]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115526989.171, "dur": 2.518, + "args": { + "External id": 230050,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 1024]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 31337, + "ts": 667115526992.420, "dur": 15.353, + "args": { + "External id": 230051,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 31337, + "ts": 667115526993.772, "dur": 13.552, + "args": { + "External id": 230052,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115527009.311, "dur": 4.133, + "args": { + "External id": 230053,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], [], []], "Ev Idx": 164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115527012.385, "dur": 0.777, + "args": { + "External id": 230054,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[4194304, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4194304, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], []], "Ev Idx": 165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115527014.190, "dur": 21.206, + "args": { + "External id": 230055,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115527044.816, "dur": 50.941, + "args": { + "External id": 230056,"Record function id": 0, "Sequence number": 2757936, "Fwd thread id": 1, "Ev Idx": 167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115527045.720, "dur": 47.642, + "args": { + "External id": 230057,"Sequence number": 2757936, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 168 + } + }, + { + "ph": "f", "id": 20, "pid": 4183440, "tid": 31337, "ts": 667115527045.720, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 4183440, "tid": 31337, + "ts": 667115527047.840, "dur": 45.221, + "args": { + "External id": 230058,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "2", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], []], "Ev Idx": 169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 31337, + "ts": 667115527049.102, "dur": 18.208, + "args": { + "External id": 230059,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115527051.722, "dur": 2.645, + "args": { + "External id": 230060,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 31337, + "ts": 667115527055.037, "dur": 12.013, + "args": { + "External id": 230061,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 31337, + "ts": 667115527055.878, "dur": 10.860, + "args": { + "External id": 230062,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], []], "Ev Idx": 173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183440, "tid": 31337, + "ts": 667115527068.185, "dur": 6.079, + "args": { + "External id": 230063,"Record function id": 0, "Concrete Inputs": ["", "2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], []], "Input Dims": [[16, 4096, 4, 1024], [], []], "Ev Idx": 174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115527071.946, "dur": 1.887, + "args": { + "External id": 230064,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[16777216, 4096, 1]", "1024"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115527075.066, "dur": 17.467, + "args": { + "External id": 230065,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115527099.487, "dur": 66.183, + "args": { + "External id": 230066,"Record function id": 0, "Sequence number": 2757935, "Fwd thread id": 1, "Ev Idx": 177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115527100.967, "dur": 62.054, + "args": { + "External id": 230067,"Sequence number": 2757935, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 178 + } + }, + { + "ph": "f", "id": 21, "pid": 4183440, "tid": 31337, "ts": 667115527100.967, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183440, "tid": 31337, + "ts": 667115527102.034, "dur": 60.652, + "args": { + "External id": 230068,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], [], []], "Ev Idx": 179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 31337, + "ts": 667115527103.080, "dur": 16.366, + "args": { + "External id": 230069,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115527105.724, "dur": 2.146, + "args": { + "External id": 230070,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 31337, + "ts": 667115527108.444, "dur": 10.760, + "args": { + "External id": 230071,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 31337, + "ts": 667115527109.164, "dur": 9.733, + "args": { + "External id": 230072,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], []], "Ev Idx": 183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115527120.328, "dur": 3.262, + "args": { + "External id": 230073,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], []], "Ev Idx": 184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115527122.765, "dur": 0.647, + "args": { + "External id": 230074,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "[16777216, 4096, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115527124.361, "dur": 37.575, + "args": { + "External id": 230075,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], [16, 4096, 4, 1024], []], "Ev Idx": 186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115527169.572, "dur": 76.972, + "args": { + "External id": 230076,"Record function id": 0, "Sequence number": 2757934, "Fwd thread id": 1, "Ev Idx": 187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115527170.942, "dur": 60.280, + "args": { + "External id": 230077,"Sequence number": 2757934, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 188 + } + }, + { + "ph": "f", "id": 22, "pid": 4183440, "tid": 31337, "ts": 667115527170.942, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183440, "tid": 31337, + "ts": 667115527173.873, "dur": 57.001, + "args": { + "External id": 230078,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], [], []], "Ev Idx": 189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 31337, + "ts": 667115527174.807, "dur": 17.433, + "args": { + "External id": 230079,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115527177.159, "dur": 1.616, + "args": { + "External id": 230080,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 31337, + "ts": 667115527179.239, "dur": 12.744, + "args": { + "External id": 230081,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 31337, + "ts": 667115527179.859, "dur": 11.740, + "args": { + "External id": 230082,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], []], "Ev Idx": 193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115527193.072, "dur": 1.564, + "args": { + "External id": 230083,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], []], "Ev Idx": 194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115527193.934, "dur": 0.527, + "args": { + "External id": 230084,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "[16777216, 4096, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115527195.229, "dur": 35.087, + "args": { + "External id": 230085,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], [16, 4096, 4, 1024], []], "Ev Idx": 196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 31337, + "ts": 667115527234.462, "dur": 10.758, + "args": { + "External id": 230086,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], [16, 4096, 4, 1024], []], "Ev Idx": 197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115527252.446, "dur": 28.465, + "args": { + "External id": 230087,"Record function id": 0, "Sequence number": 2757933, "Fwd thread id": 1, "Ev Idx": 198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115527253.486, "dur": 0.647, + "args": { + "External id": 230088,"Sequence number": 2757933, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 199 + } + }, + { + "ph": "f", "id": 23, "pid": 4183440, "tid": 31337, "ts": 667115527253.486, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 31337, + "ts": 667115527255.885, "dur": 21.229, + "args": { + "External id": 230089,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 31337, + "ts": 667115527258.909, "dur": 17.796, + "args": { + "External id": 230090,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115527262.921, "dur": 0.543, + "args": { + "External id": 230091,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115527284.732, "dur": 1510.258, + "args": { + "External id": 230092,"Record function id": 0, "Sequence number": 2757932, "Fwd thread id": 1, "Ev Idx": 203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115527295.030, "dur": 1474.690, + "args": { + "External id": 230093,"Sequence number": 2757932, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 204 + } + }, + { + "ph": "f", "id": 24, "pid": 4183440, "tid": 31337, "ts": 667115527295.030, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115527316.958, "dur": 1.758, + "args": { + "External id": 230094,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115527320.646, "dur": 1370.754, + "args": { + "External id": 230095,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115527321.888, "dur": 1369.272, + "args": { + "External id": 230096,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115527323.553, "dur": 3.283, + "args": { + "External id": 230097,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115527327.644, "dur": 1362.436, + "args": { + "External id": 230098,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 4183440, "tid": 31337, + "ts": 667115528695.761, "dur": 0.284, + "args": { + "External id": 230099,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 4183440, "tid": 31337, + "ts": 667115528696.980, "dur": 2.109, + "args": { + "External id": 230100,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 4183440, "tid": 31337, + "ts": 667115528698.259, "dur": 0.712, + "args": { + "External id": 230101,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 4183440, "tid": 31337, + "ts": 667115528702.755, "dur": 20.137, + "args": { + "External id": 230102,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 4183440, "tid": 31337, + "ts": 667115528726.512, "dur": 37.344, + "args": { + "External id": 230103,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 4183440, "tid": 31337, + "ts": 667115528727.641, "dur": 36.031, + "args": { + "External id": 230104,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 4183440, "tid": 31337, + "ts": 667115528728.595, "dur": 34.670, + "args": { + "External id": 230105,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 31337, + "ts": 667115528778.368, "dur": 13.150, + "args": { + "External id": 230106,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115528809.019, "dur": 11.678, + "args": { + "External id": 230107,"Record function id": 0, "Ev Idx": 218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115528811.152, "dur": 7.839, + "args": { + "External id": 230108,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115528814.411, "dur": 3.770, + "args": { + "External id": 230109,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115528815.160, "dur": 2.898, + "args": { + "External id": 230110,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115528824.142, "dur": 8.621, + "args": { + "External id": 230111,"Record function id": 0, "Sequence number": 2757931, "Fwd thread id": 1, "Ev Idx": 222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115528825.137, "dur": 5.527, + "args": { + "External id": 230112,"Sequence number": 2757931, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 223 + } + }, + { + "ph": "f", "id": 25, "pid": 4183440, "tid": 31337, "ts": 667115528825.137, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115528826.949, "dur": 3.493, + "args": { + "External id": 230113,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115528827.947, "dur": 2.387, + "args": { + "External id": 230114,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115528835.987, "dur": 59.450, + "args": { + "External id": 230115,"Record function id": 0, "Sequence number": 2757930, "Fwd thread id": 1, "Ev Idx": 226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115528836.988, "dur": 54.342, + "args": { + "External id": 230116,"Sequence number": 2757930, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 227 + } + }, + { + "ph": "f", "id": 26, "pid": 4183440, "tid": 31337, "ts": 667115528836.988, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183440, "tid": 31337, + "ts": 667115528840.230, "dur": 50.762, + "args": { + "External id": 230117,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], [], [], []], "Ev Idx": 228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 31337, + "ts": 667115528844.173, "dur": 22.296, + "args": { + "External id": 230118,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 1024]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115528845.233, "dur": 2.481, + "args": { + "External id": 230119,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 1024]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 31337, + "ts": 667115528848.502, "dur": 17.713, + "args": { + "External id": 230120,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 31337, + "ts": 667115528849.431, "dur": 16.276, + "args": { + "External id": 230121,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115528867.892, "dur": 4.281, + "args": { + "External id": 230122,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], [], []], "Ev Idx": 233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115528871.088, "dur": 0.888, + "args": { + "External id": 230123,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[4194304, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4194304, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], []], "Ev Idx": 234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115528873.076, "dur": 17.155, + "args": { + "External id": 230124,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115528899.150, "dur": 51.944, + "args": { + "External id": 230125,"Record function id": 0, "Sequence number": 2757929, "Fwd thread id": 1, "Ev Idx": 236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115528900.070, "dur": 48.196, + "args": { + "External id": 230126,"Sequence number": 2757929, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 237 + } + }, + { + "ph": "f", "id": 27, "pid": 4183440, "tid": 31337, "ts": 667115528900.070, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 4183440, "tid": 31337, + "ts": 667115528901.935, "dur": 46.106, + "args": { + "External id": 230127,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "2", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], []], "Ev Idx": 238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 31337, + "ts": 667115528903.353, "dur": 18.696, + "args": { + "External id": 230128,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115528908.160, "dur": 2.144, + "args": { + "External id": 230129,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 31337, + "ts": 667115528910.869, "dur": 10.927, + "args": { + "External id": 230130,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 31337, + "ts": 667115528911.670, "dur": 9.712, + "args": { + "External id": 230131,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], []], "Ev Idx": 242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183440, "tid": 31337, + "ts": 667115528923.120, "dur": 5.179, + "args": { + "External id": 230132,"Record function id": 0, "Concrete Inputs": ["", "2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], []], "Input Dims": [[16, 4096, 4, 1024], [], []], "Ev Idx": 243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115528927.104, "dur": 0.792, + "args": { + "External id": 230133,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115528929.049, "dur": 18.451, + "args": { + "External id": 230134,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115528954.668, "dur": 71.242, + "args": { + "External id": 230135,"Record function id": 0, "Sequence number": 2757928, "Fwd thread id": 1, "Ev Idx": 246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115528955.796, "dur": 67.288, + "args": { + "External id": 230136,"Sequence number": 2757928, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 247 + } + }, + { + "ph": "f", "id": 28, "pid": 4183440, "tid": 31337, "ts": 667115528955.796, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183440, "tid": 31337, + "ts": 667115528956.996, "dur": 65.768, + "args": { + "External id": 230137,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], [], []], "Ev Idx": 248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 31337, + "ts": 667115528958.454, "dur": 18.261, + "args": { + "External id": 230138,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115528962.412, "dur": 2.505, + "args": { + "External id": 230139,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 31337, + "ts": 667115528965.514, "dur": 10.958, + "args": { + "External id": 230140,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 31337, + "ts": 667115528966.673, "dur": 9.421, + "args": { + "External id": 230141,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], []], "Ev Idx": 252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115528977.543, "dur": 3.403, + "args": { + "External id": 230142,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], []], "Ev Idx": 253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115528978.799, "dur": 2.012, + "args": { + "External id": 230143,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "[16777216, 4096, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115528981.742, "dur": 40.363, + "args": { + "External id": 230144,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], [16, 4096, 4, 1024], []], "Ev Idx": 255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115529029.431, "dur": 81.958, + "args": { + "External id": 230145,"Record function id": 0, "Sequence number": 2757927, "Fwd thread id": 1, "Ev Idx": 256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115529030.512, "dur": 64.022, + "args": { + "External id": 230146,"Sequence number": 2757927, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 257 + } + }, + { + "ph": "f", "id": 29, "pid": 4183440, "tid": 31337, "ts": 667115529030.512, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 4183440, "tid": 31337, + "ts": 667115529032.018, "dur": 62.187, + "args": { + "External id": 230147,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], [], []], "Ev Idx": 258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 31337, + "ts": 667115529032.807, "dur": 20.987, + "args": { + "External id": 230148,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115529036.946, "dur": 1.656, + "args": { + "External id": 230149,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 1024]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 31337, + "ts": 667115529041.848, "dur": 11.674, + "args": { + "External id": 230150,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 31337, + "ts": 667115529043.804, "dur": 9.309, + "args": { + "External id": 230151,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], []], "Ev Idx": 262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115529054.717, "dur": 2.900, + "args": { + "External id": 230152,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], []], "Ev Idx": 263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115529057.056, "dur": 0.417, + "args": { + "External id": 230153,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "[16777216, 4096, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115529058.199, "dur": 35.265, + "args": { + "External id": 230154,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], [16, 4096, 4, 1024], []], "Ev Idx": 265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 31337, + "ts": 667115529097.494, "dur": 12.217, + "args": { + "External id": 230155,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [16777216, 4096, 1024, 1], []], "Input Dims": [[16, 4096, 4, 1024], [16, 4096, 4, 1024], []], "Ev Idx": 266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115529116.067, "dur": 321.618, + "args": { + "External id": 230156,"Record function id": 0, "Sequence number": 2757926, "Fwd thread id": 1, "Ev Idx": 267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115529117.227, "dur": 311.805, + "args": { + "External id": 230157,"Sequence number": 2757926, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 268 + } + }, + { + "ph": "f", "id": 30, "pid": 4183440, "tid": 31337, "ts": 667115529117.227, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115529267.606, "dur": 40.198, + "args": { + "External id": 230158,"kernel_hash": "cwn2qo4ncl2qi3v5pz4fikdhukjhcljwbjylpte65zey6zjf64nh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "262144", "1024", "1", "1986", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wn/cwn2qo4ncl2qi3v5pz4fikdhukjhcljwbjylpte65zey6zjf64nh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[262144, 1024], [1024], [262144, 1024], [262144, 1024], [132, 1024], [262144], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_0", "pid": 4183440, "tid": 31337, + "ts": 667115529337.968, "dur": 28.643, + "args": { + "External id": 230159,"kernel_hash": "c7dnwfbgxph4ok5pxyk4aw6r2nsyeyyk2enf3jei5vygmjcp4okc", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/7d/c7dnwfbgxph4ok5pxyk4aw6r2nsyeyyk2enf3jei5vygmjcp4okc.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_1", "pid": 4183440, "tid": 31337, + "ts": 667115529386.854, "dur": 19.765, + "args": { + "External id": 230160,"kernel_hash": "c4qb7fuzp2dt5bkszd6eq3yu47c3lgrdyzhh3yljx7xg4duul7x4", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/4q/c4qb7fuzp2dt5bkszd6eq3yu47c3lgrdyzhh3yljx7xg4duul7x4.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115529445.391, "dur": 11.197, + "args": { + "External id": 230161,"Record function id": 0, "Ev Idx": 272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115529447.220, "dur": 8.547, + "args": { + "External id": 230162,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115529449.816, "dur": 5.189, + "args": { + "External id": 230163,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115529452.738, "dur": 2.121, + "args": { + "External id": 230164,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: StackBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115529460.547, "dur": 28.529, + "args": { + "External id": 230165,"Record function id": 0, "Sequence number": 2757925, "Fwd thread id": 1, "Ev Idx": 276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "StackBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115529461.654, "dur": 20.746, + "args": { + "External id": 230166,"Sequence number": 2757925, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1024, 1]], "Input Dims": [[16, 4096, 4, 1024]], "Ev Idx": 277 + } + }, + { + "ph": "f", "id": 31, "pid": 4183440, "tid": 31337, "ts": 667115529461.654, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183440, "tid": 31337, + "ts": 667115529463.632, "dur": 6.895, + "args": { + "External id": 230167,"Record function id": 0, "Concrete Inputs": ["", "-2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], []], "Input Dims": [[16, 4096, 4, 1024], [], []], "Ev Idx": 278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115529467.953, "dur": 1.133, + "args": { + "External id": 230168,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183440, "tid": 31337, + "ts": 667115529471.041, "dur": 3.652, + "args": { + "External id": 230169,"Record function id": 0, "Concrete Inputs": ["", "-2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], []], "Input Dims": [[16, 4096, 4, 1024], [], []], "Ev Idx": 280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115529473.554, "dur": 0.476, + "args": { + "External id": 230170,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[16777216, 4096, 1]", "1024"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183440, "tid": 31337, + "ts": 667115529475.062, "dur": 2.364, + "args": { + "External id": 230171,"Record function id": 0, "Concrete Inputs": ["", "-2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], []], "Input Dims": [[16, 4096, 4, 1024], [], []], "Ev Idx": 282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115529476.156, "dur": 0.582, + "args": { + "External id": 230172,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[16777216, 4096, 1]", "2048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183440, "tid": 31337, + "ts": 667115529477.904, "dur": 3.947, + "args": { + "External id": 230173,"Record function id": 0, "Concrete Inputs": ["", "-2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], []], "Input Dims": [[16, 4096, 4, 1024], [], []], "Ev Idx": 284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115529480.519, "dur": 0.645, + "args": { + "External id": 230174,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[16777216, 4096, 1]", "3072"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115529511.926, "dur": 5.997, + "args": { + "External id": 230175,"Record function id": 0, "Sequence number": 2757924, "Fwd thread id": 1, "Ev Idx": 286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115529513.449, "dur": 1.238, + "args": { + "External id": 230176,"Sequence number": 2757924, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 287 + } + }, + { + "ph": "f", "id": 32, "pid": 4183440, "tid": 31337, "ts": 667115529513.449, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115529522.129, "dur": 528.483, + "args": { + "External id": 230177,"Record function id": 0, "Sequence number": 2757923, "Fwd thread id": 1, "Ev Idx": 288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115529523.651, "dur": 514.604, + "args": { + "External id": 230178,"Sequence number": 2757923, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 289 + } + }, + { + "ph": "f", "id": 33, "pid": 4183440, "tid": 31337, "ts": 667115529523.651, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115529562.506, "dur": 12.862, + "args": { + "External id": 230179,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 4183440, "tid": 31337, + "ts": 667115529569.928, "dur": 5.131, + "args": { + "External id": 230180,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]", "[4096, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[16777216, 4096, 1], [], []], "Input Dims": [[16, 4096, 1024], [], []], "Ev Idx": 291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115529579.265, "dur": 9.172, + "args": { + "External id": 230181,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115529581.565, "dur": 6.019, + "args": { + "External id": 230182,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2816, 1], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115529584.926, "dur": 2.429, + "args": { + "External id": 230183,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 31337, + "ts": 667115529592.231, "dur": 153.766, + "args": { + "External id": 230184,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [1, 2816], []], "Input Dims": [[65536, 1024], [2816, 1024], []], "Ev Idx": 295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115529593.351, "dur": 3.293, + "args": { + "External id": 230185,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2816]], "Input Dims": [[2816, 1024]], "Ev Idx": 296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115529594.127, "dur": 1.957, + "args": { + "External id": 230186,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2816], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115529595.064, "dur": 0.924, + "args": { + "External id": 230187,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[2816, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2816], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 31337, + "ts": 667115529597.991, "dur": 147.193, + "args": { + "External id": 230188,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816]], "Ev Idx": 299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115529599.851, "dur": 143.550, + "args": { + "External id": 230189,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816]], "Ev Idx": 300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 31337, + "ts": 667115529755.671, "dur": 6.486, + "args": { + "External id": 230190,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [11534336, 2816, 1]], "Input Dims": [[65536, 2816], [16, 4096, 2816]], "Ev Idx": 301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115529759.009, "dur": 3.043, + "args": { + "External id": 230191,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1], []], "Input Dims": [[65536, 2816], []], "Ev Idx": 302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115529797.450, "dur": 6.167, + "args": { + "External id": 230192,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2816]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115529804.581, "dur": 2.229, + "args": { + "External id": 230193,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2816]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115529807.561, "dur": 1.899, + "args": { + "External id": 230194,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2816]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115529850.460, "dur": 3.126, + "args": { + "External id": 230195,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115529851.732, "dur": 1.714, + "args": { + "External id": 230196,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 4183440, "tid": 31337, + "ts": 667115529880.631, "dur": 135.519, + "args": { + "External id": 230197,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[4096, 1], [2816, 1]], []], "Input Dims": [[], [[65536, 1024], [65536, 2816]], []], "Ev Idx": 308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 31337, + "ts": 667115529887.405, "dur": 9.946, + "args": { + "External id": 230198,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115529891.990, "dur": 3.399, + "args": { + "External id": 230199,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024, 1]", "[4096, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115529900.509, "dur": 7.415, + "args": { + "External id": 230200,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1, 1], []], "Input Dims": [[65536, 1024, 1], []], "Ev Idx": 311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115529906.866, "dur": 0.451, + "args": { + "External id": 230201,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1, 65536]", "[1, 1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1, 1], [], [], []], "Input Dims": [[65536, 1024, 1], [], [], []], "Ev Idx": 312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 31337, + "ts": 667115529909.832, "dur": 3.479, + "args": { + "External id": 230202,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], []], "Input Dims": [[65536, 2816], []], "Ev Idx": 313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115529911.937, "dur": 0.955, + "args": { + "External id": 230203,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816, 1]", "[2816, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[65536, 2816], [], [], []], "Ev Idx": 314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115529914.607, "dur": 2.874, + "args": { + "External id": 230204,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1, 1], []], "Input Dims": [[65536, 2816, 1], []], "Ev Idx": 315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115529916.627, "dur": 0.523, + "args": { + "External id": 230205,"Record function id": 0, "Concrete Inputs": ["", "[1, 2816, 65536]", "[1, 1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1, 1], [], [], []], "Input Dims": [[65536, 2816, 1], [], [], []], "Ev Idx": 316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115529924.342, "dur": 3.085, + "args": { + "External id": 230206,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 4096], []], "Input Dims": [[1024, 1, 65536], []], "Ev Idx": 317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115529926.476, "dur": 0.616, + "args": { + "External id": 230207,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536, 1]", "[1, 4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 4096], [], [], []], "Input Dims": [[1024, 1, 65536], [], [], []], "Ev Idx": 318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115529928.458, "dur": 6.436, + "args": { + "External id": 230208,"Record function id": 0, "Concrete Inputs": ["", "[1, 1024, 65536]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 4096, 1], []], "Input Dims": [[1024, 65536, 1], []], "Ev Idx": 319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 4183440, "tid": 31337, + "ts": 667115529932.552, "dur": 2.124, + "args": { + "External id": 230209,"Record function id": 0, "Concrete Inputs": ["", "[1, 1024, 65536]", "[1024, 1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 4096, 1], [], []], "Input Dims": [[1024, 65536, 1], [], []], "Ev Idx": 320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115529936.160, "dur": 3.076, + "args": { + "External id": 230210,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 2816], []], "Input Dims": [[1, 2816, 65536], []], "Ev Idx": 321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115529938.173, "dur": 0.765, + "args": { + "External id": 230211,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816, 1]", "[2816, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 2816], [], [], []], "Input Dims": [[1, 2816, 65536], [], [], []], "Ev Idx": 322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115529940.275, "dur": 2.307, + "args": { + "External id": 230212,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1, 1], []], "Input Dims": [[65536, 2816, 1], []], "Ev Idx": 323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115529941.421, "dur": 1.074, + "args": { + "External id": 230213,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1, 1], []], "Input Dims": [[65536, 2816, 1], []], "Ev Idx": 324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115529944.541, "dur": 60.194, + "args": { + "External id": 230214,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1, 4096], [184549376, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816]], "Ev Idx": 325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115530006.606, "dur": 1.069, + "args": { + "External id": 230215,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2883584, 2816, 1], []], "Input Dims": [[1, 1024, 2816], []], "Ev Idx": 326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115530008.776, "dur": 3.180, + "args": { + "External id": 230216,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 2816, 1], []], "Input Dims": [[1024, 1, 2816], []], "Ev Idx": 327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115530010.817, "dur": 0.629, + "args": { + "External id": 230217,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816, 1]", "[2816, 1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 2816, 1], [], [], []], "Input Dims": [[1024, 1, 2816], [], [], []], "Ev Idx": 328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115530014.038, "dur": 0.897, + "args": { + "External id": 230218,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1, 2816], []], "Input Dims": [[1024, 2816, 1], []], "Ev Idx": 329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115530062.900, "dur": 9.831, + "args": { + "External id": 230219,"Record function id": 0, "Ev Idx": 330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115530065.126, "dur": 6.879, + "args": { + "External id": 230220,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115530067.703, "dur": 3.406, + "args": { + "External id": 230221,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115530068.676, "dur": 2.324, + "args": { + "External id": 230222,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530076.461, "dur": 8.248, + "args": { + "External id": 230223,"Record function id": 0, "Sequence number": 2757922, "Fwd thread id": 1, "Ev Idx": 334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530077.616, "dur": 4.272, + "args": { + "External id": 230224,"Sequence number": 2757922, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[11534336, 2816, 1]], "Input Dims": [[16, 4096, 2816]], "Ev Idx": 335 + } + }, + { + "ph": "f", "id": 34, "pid": 4183440, "tid": 31337, "ts": 667115530077.616, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115530079.147, "dur": 2.526, + "args": { + "External id": 230225,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115530080.449, "dur": 1.079, + "args": { + "External id": 230226,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530088.548, "dur": 116.268, + "args": { + "External id": 230227,"Record function id": 0, "Sequence number": 2757921, "Fwd thread id": 1, "Ev Idx": 338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530091.425, "dur": 106.271, + "args": { + "External id": 230228,"Sequence number": 2757921, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[65536, 2816]], "Ev Idx": 339 + } + }, + { + "ph": "f", "id": 35, "pid": 4183440, "tid": 31337, "ts": 667115530091.425, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115530095.452, "dur": 3.950, + "args": { + "External id": 230229,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[65536, 2816]], "Ev Idx": 340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115530096.749, "dur": 2.128, + "args": { + "External id": 230230,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2816, 1], [], []], "Input Dims": [[65536, 2816], [], []], "Ev Idx": 341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115530098.188, "dur": 0.476, + "args": { + "External id": 230231,"Record function id": 0, "Concrete Inputs": ["", "[2816, 65536]", "[1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[65536, 2816], [], [], []], "Ev Idx": 342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115530100.845, "dur": 39.964, + "args": { + "External id": 230232,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024]], "Ev Idx": 343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115530142.109, "dur": 5.156, + "args": { + "External id": 230233,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115530142.656, "dur": 3.961, + "args": { + "External id": 230234,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115530145.559, "dur": 0.878, + "args": { + "External id": 230235,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115530148.766, "dur": 4.693, + "args": { + "External id": 230236,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115530149.544, "dur": 3.445, + "args": { + "External id": 230237,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115530150.800, "dur": 2.079, + "args": { + "External id": 230238,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115530153.909, "dur": 42.944, + "args": { + "External id": 230239,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024]], "Ev Idx": 350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530209.509, "dur": 8.362, + "args": { + "External id": 230240,"Record function id": 0, "Sequence number": 2757920, "Fwd thread id": 1, "Ev Idx": 351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530210.347, "dur": 5.957, + "args": { + "External id": 230241,"Sequence number": 2757920, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 352 + } + }, + { + "ph": "f", "id": 36, "pid": 4183440, "tid": 31337, "ts": 667115530210.347, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115530212.060, "dur": 4.102, + "args": { + "External id": 230242,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115530214.948, "dur": 1.112, + "args": { + "External id": 230243,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530221.613, "dur": 7.771, + "args": { + "External id": 230244,"Record function id": 0, "Sequence number": 2757919, "Fwd thread id": 1, "Ev Idx": 355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530222.522, "dur": 4.855, + "args": { + "External id": 230245,"Sequence number": 2757919, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 356 + } + }, + { + "ph": "f", "id": 37, "pid": 4183440, "tid": 31337, "ts": 667115530222.522, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115530223.640, "dur": 3.538, + "args": { + "External id": 230246,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115530224.402, "dur": 2.231, + "args": { + "External id": 230247,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115530226.087, "dur": 0.415, + "args": { + "External id": 230248,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115530233.555, "dur": 5.685, + "args": { + "External id": 230249,"Record function id": 0, "Ev Idx": 360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115530235.243, "dur": 3.361, + "args": { + "External id": 230250,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115530236.236, "dur": 2.024, + "args": { + "External id": 230251,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115530236.844, "dur": 1.324, + "args": { + "External id": 230252,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530243.773, "dur": 8.320, + "args": { + "External id": 230253,"Record function id": 0, "Sequence number": 2757918, "Fwd thread id": 1, "Ev Idx": 364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530244.884, "dur": 5.453, + "args": { + "External id": 230254,"Sequence number": 2757918, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[11534336, 2816, 1]], "Input Dims": [[16, 4096, 2816]], "Ev Idx": 365 + } + }, + { + "ph": "f", "id": 38, "pid": 4183440, "tid": 31337, "ts": 667115530244.884, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115530248.377, "dur": 1.817, + "args": { + "External id": 230255,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115530249.223, "dur": 0.834, + "args": { + "External id": 230256,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530255.473, "dur": 91.284, + "args": { + "External id": 230257,"Record function id": 0, "Sequence number": 2757917, "Fwd thread id": 1, "Ev Idx": 368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530256.414, "dur": 82.634, + "args": { + "External id": 230258,"Sequence number": 2757917, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[65536, 2816]], "Ev Idx": 369 + } + }, + { + "ph": "f", "id": 39, "pid": 4183440, "tid": 31337, "ts": 667115530256.414, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115530258.060, "dur": 4.569, + "args": { + "External id": 230259,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[65536, 2816]], "Ev Idx": 370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115530258.782, "dur": 3.425, + "args": { + "External id": 230260,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2816, 1], [], []], "Input Dims": [[65536, 2816], [], []], "Ev Idx": 371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115530261.629, "dur": 0.438, + "args": { + "External id": 230261,"Record function id": 0, "Concrete Inputs": ["", "[2816, 65536]", "[1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[65536, 2816], [], [], []], "Ev Idx": 372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115530263.254, "dur": 27.285, + "args": { + "External id": 230262,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024]], "Ev Idx": 373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115530291.514, "dur": 5.799, + "args": { + "External id": 230263,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115530292.411, "dur": 4.345, + "args": { + "External id": 230264,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115530293.996, "dur": 2.631, + "args": { + "External id": 230265,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115530298.628, "dur": 4.400, + "args": { + "External id": 230266,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115530299.146, "dur": 3.344, + "args": { + "External id": 230267,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115530301.974, "dur": 0.449, + "args": { + "External id": 230268,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115530303.591, "dur": 34.692, + "args": { + "External id": 230269,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024]], "Ev Idx": 380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530351.028, "dur": 34.040, + "args": { + "External id": 230270,"Record function id": 0, "Sequence number": 2757916, "Fwd thread id": 1, "Ev Idx": 381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530351.963, "dur": 4.236, + "args": { + "External id": 230271,"Sequence number": 2757916, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 382 + } + }, + { + "ph": "f", "id": 40, "pid": 4183440, "tid": 31337, "ts": 667115530351.963, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115530353.735, "dur": 2.338, + "args": { + "External id": 230272,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115530354.757, "dur": 1.193, + "args": { + "External id": 230273,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 4183440, "tid": 31337, + "ts": 667115530359.248, "dur": 23.377, + "args": { + "External id": 230274,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530388.832, "dur": 9.742, + "args": { + "External id": 230275,"Record function id": 0, "Sequence number": 2757915, "Fwd thread id": 1, "Ev Idx": 386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530389.747, "dur": 6.727, + "args": { + "External id": 230276,"Sequence number": 2757915, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 387 + } + }, + { + "ph": "f", "id": 41, "pid": 4183440, "tid": 31337, "ts": 667115530389.747, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115530392.432, "dur": 3.781, + "args": { + "External id": 230277,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115530393.150, "dur": 2.528, + "args": { + "External id": 230278,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115530394.961, "dur": 0.569, + "args": { + "External id": 230279,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115530402.561, "dur": 5.365, + "args": { + "External id": 230280,"Record function id": 0, "Ev Idx": 391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115530404.072, "dur": 3.359, + "args": { + "External id": 230281,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115530405.046, "dur": 1.901, + "args": { + "External id": 230282,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115530405.592, "dur": 1.254, + "args": { + "External id": 230283,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115530412.158, "dur": 478.363, + "args": { + "External id": 230284,"Record function id": 0, "Sequence number": 2757914, "Fwd thread id": 1, "Ev Idx": 395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115530414.120, "dur": 463.190, + "args": { + "External id": 230285,"Sequence number": 2757914, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [16777216, 4096, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 396 + } + }, + { + "ph": "f", "id": 42, "pid": 4183440, "tid": 31337, "ts": 667115530414.120, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183440, "tid": 31337, + "ts": 667115530435.711, "dur": 33.582, + "args": { + "External id": 230286,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 31337, + "ts": 667115530437.087, "dur": 32.019, + "args": { + "External id": 230287,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115530440.574, "dur": 5.446, + "args": { + "External id": 230288,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], [], [], []], "Ev Idx": 399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115530443.115, "dur": 2.427, + "args": { + "External id": 230289,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 1024]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115530447.565, "dur": 21.053, + "args": { + "External id": 230290,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115530481.767, "dur": 4.730, + "args": { + "External id": 230291,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115530483.321, "dur": 3.031, + "args": { + "External id": 230292,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115530490.173, "dur": 21.570, + "args": { + "External id": 230293,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115530510.217, "dur": 1.265, + "args": { + "External id": 230294,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115530526.818, "dur": 3.640, + "args": { + "External id": 230295,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115530542.298, "dur": 2.670, + "args": { + "External id": 230296,"Record function id": 0, "Concrete Inputs": ["[132, 1024]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115530759.985, "dur": 3.700, + "args": { + "External id": 230297,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 1024]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[132, 1024], []], "Ev Idx": 408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 31337, + "ts": 667115530768.219, "dur": 36.759, + "args": { + "External id": 230298,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[135168, 1024, 1], [], [], []], "Input Dims": [[1, 132, 1024], [], [], []], "Ev Idx": 409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115530779.568, "dur": 1.010, + "args": { + "External id": 230299,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 1024]", "[1024, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1, 1024], [], [], []], "Ev Idx": 410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115530811.124, "dur": 32.383, + "args": { + "External id": 230300,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[1, 1024], [], [], [], [], []], "Ev Idx": 411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115530813.207, "dur": 30.059, + "args": { + "External id": 230301,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], [], []], "Input Dims": [[1, 1024], [], [], [], [], [], []], "Ev Idx": 412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115530817.927, "dur": 3.844, + "args": { + "External id": 230302,"Record function id": 0, "Concrete Inputs": ["[1, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115530825.675, "dur": 16.975, + "args": { + "External id": 230303,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[1, 1024], [1, 1024], []], "Ev Idx": 414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 31337, + "ts": 667115530848.232, "dur": 2.871, + "args": { + "External id": 230304,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1]], "Input Dims": [[1, 1024], [1024]], "Ev Idx": 415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115530849.736, "dur": 1.238, + "args": { + "External id": 230305,"Record function id": 0, "Concrete Inputs": ["", "[1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[1, 1024], []], "Ev Idx": 416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115530858.053, "dur": 4.280, + "args": { + "External id": 230306,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115530859.101, "dur": 3.134, + "args": { + "External id": 230307,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115530864.510, "dur": 1.828, + "args": { + "External id": 230308,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115530865.570, "dur": 0.682, + "args": { + "External id": 230309,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115530904.667, "dur": 9.496, + "args": { + "External id": 230310,"Record function id": 0, "Ev Idx": 421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115530907.137, "dur": 6.154, + "args": { + "External id": 230311,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115530909.470, "dur": 2.823, + "args": { + "External id": 230312,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115530910.503, "dur": 1.708, + "args": { + "External id": 230313,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530918.320, "dur": 9.111, + "args": { + "External id": 230314,"Record function id": 0, "Sequence number": 2757913, "Fwd thread id": 1, "Ev Idx": 425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530920.058, "dur": 4.102, + "args": { + "External id": 230315,"Sequence number": 2757913, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 426 + } + }, + { + "ph": "f", "id": 43, "pid": 4183440, "tid": 31337, "ts": 667115530920.058, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115530921.916, "dur": 2.007, + "args": { + "External id": 230316,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115530922.811, "dur": 0.969, + "args": { + "External id": 230317,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530933.235, "dur": 140.824, + "args": { + "External id": 230318,"Record function id": 0, "Sequence number": 2757912, "Fwd thread id": 1, "Ev Idx": 429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115530934.184, "dur": 135.476, + "args": { + "External id": 230319,"Sequence number": 2757912, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 430 + } + }, + { + "ph": "f", "id": 44, "pid": 4183440, "tid": 31337, "ts": 667115530934.184, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115530936.929, "dur": 5.267, + "args": { + "External id": 230320,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115530938.509, "dur": 3.068, + "args": { + "External id": 230321,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[65536, 1024], [], []], "Ev Idx": 432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115530940.548, "dur": 0.827, + "args": { + "External id": 230322,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115530943.371, "dur": 74.318, + "args": { + "External id": 230323,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024]], "Ev Idx": 434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115531019.140, "dur": 9.594, + "args": { + "External id": 230324,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115531022.485, "dur": 5.669, + "args": { + "External id": 230325,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115531024.413, "dur": 3.559, + "args": { + "External id": 230326,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115531030.013, "dur": 3.256, + "args": { + "External id": 230327,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115531030.687, "dur": 1.834, + "args": { + "External id": 230328,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115531032.013, "dur": 0.409, + "args": { + "External id": 230329,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115531033.944, "dur": 34.748, + "args": { + "External id": 230330,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115531078.556, "dur": 10.153, + "args": { + "External id": 230331,"Record function id": 0, "Sequence number": 2757911, "Fwd thread id": 1, "Ev Idx": 442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115531079.334, "dur": 7.396, + "args": { + "External id": 230332,"Sequence number": 2757911, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 443 + } + }, + { + "ph": "f", "id": 45, "pid": 4183440, "tid": 31337, "ts": 667115531079.334, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115531082.343, "dur": 4.232, + "args": { + "External id": 230333,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115531083.433, "dur": 2.996, + "args": { + "External id": 230334,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115531092.455, "dur": 8.203, + "args": { + "External id": 230335,"Record function id": 0, "Sequence number": 2757910, "Fwd thread id": 1, "Ev Idx": 446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115531093.694, "dur": 4.675, + "args": { + "External id": 230336,"Sequence number": 2757910, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 447 + } + }, + { + "ph": "f", "id": 46, "pid": 4183440, "tid": 31337, "ts": 667115531093.694, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115531094.508, "dur": 3.650, + "args": { + "External id": 230337,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115531095.196, "dur": 2.463, + "args": { + "External id": 230338,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115531097.062, "dur": 0.459, + "args": { + "External id": 230339,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115531104.671, "dur": 7.888, + "args": { + "External id": 230340,"Record function id": 0, "Ev Idx": 451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115531106.390, "dur": 5.657, + "args": { + "External id": 230341,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115531107.337, "dur": 4.402, + "args": { + "External id": 230342,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115531110.040, "dur": 1.538, + "args": { + "External id": 230343,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115531115.843, "dur": 6.009, + "args": { + "External id": 230344,"Record function id": 0, "Sequence number": 2757909, "Fwd thread id": 1, "Ev Idx": 455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115531116.688, "dur": 3.345, + "args": { + "External id": 230345,"Sequence number": 2757909, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 456 + } + }, + { + "ph": "f", "id": 47, "pid": 4183440, "tid": 31337, "ts": 667115531116.688, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115531117.792, "dur": 2.091, + "args": { + "External id": 230346,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115531118.591, "dur": 1.168, + "args": { + "External id": 230347,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 4183440, "tid": 31337, + "ts": 667115531128.494, "dur": 280.759, + "args": { + "External id": 230348,"Record function id": 0, "Sequence number": 2757908, "Fwd thread id": 1, "Ev Idx": 459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 4183440, "tid": 31337, + "ts": 667115531129.861, "dur": 263.644, + "args": { + "External id": 230349,"Sequence number": 2757908, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 460 + } + }, + { + "ph": "f", "id": 48, "pid": 4183440, "tid": 31337, "ts": 667115531129.861, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115531145.226, "dur": 6.768, + "args": { + "External id": 230350,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115531147.955, "dur": 3.644, + "args": { + "External id": 230351,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115531154.223, "dur": 3.550, + "args": { + "External id": 230352,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115531155.477, "dur": 2.096, + "args": { + "External id": 230353,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115531159.213, "dur": 5.910, + "args": { + "External id": 230354,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115531161.272, "dur": 3.659, + "args": { + "External id": 230355,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115531192.503, "dur": 176.584, + "args": { + "External id": 230356,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115531277.099, "dur": 3.472, + "args": { + "External id": 230357,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115531282.380, "dur": 3.705, + "args": { + "External id": 230358,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 4183440, "tid": 31337, + "ts": 667115531381.433, "dur": 3.264, + "args": { + "External id": 230359,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 4183440, "tid": 31337, + "ts": 667115531387.469, "dur": 0.778, + "args": { + "External id": 230360,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 4183440, "tid": 31337, + "ts": 667115531390.127, "dur": 0.820, + "args": { + "External id": 230361,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115531416.421, "dur": 276.633, + "args": { + "External id": 230362,"Record function id": 0, "Sequence number": 2757907, "Fwd thread id": 1, "Ev Idx": 473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115531418.160, "dur": 230.900, + "args": { + "External id": 230363,"Sequence number": 2757907, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 474 + } + }, + { + "ph": "f", "id": 49, "pid": 4183440, "tid": 31337, "ts": 667115531418.160, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 31337, + "ts": 667115531437.299, "dur": 39.837, + "args": { + "External id": 230364,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115531440.684, "dur": 2.835, + "args": { + "External id": 230365,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115531444.671, "dur": 32.003, + "args": { + "External id": 230366,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], []], "Ev Idx": 477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115531486.687, "dur": 22.816, + "args": { + "External id": 230367,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115531488.545, "dur": 20.258, + "args": { + "External id": 230368,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115531704.063, "dur": 163.003, + "args": { + "External id": 230369,"Record function id": 0, "Sequence number": 2757906, "Fwd thread id": 1, "Ev Idx": 480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115531706.234, "dur": 155.056, + "args": { + "External id": 230370,"Sequence number": 2757906, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 481 + } + }, + { + "ph": "f", "id": 50, "pid": 4183440, "tid": 31337, "ts": 667115531706.234, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 31337, + "ts": 667115531720.245, "dur": 35.791, + "args": { + "External id": 230371,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115531723.419, "dur": 4.054, + "args": { + "External id": 230372,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115531728.798, "dur": 26.562, + "args": { + "External id": 230373,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], []], "Ev Idx": 484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115531764.017, "dur": 6.279, + "args": { + "External id": 230374,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115531766.025, "dur": 3.979, + "args": { + "External id": 230375,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115531873.333, "dur": 15.236, + "args": { + "External id": 230376,"Record function id": 0, "Sequence number": 2757905, "Fwd thread id": 1, "Ev Idx": 487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115531874.928, "dur": 10.818, + "args": { + "External id": 230377,"Sequence number": 2757905, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 488 + } + }, + { + "ph": "f", "id": 51, "pid": 4183440, "tid": 31337, "ts": 667115531874.928, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115531877.395, "dur": 8.074, + "args": { + "External id": 230378,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115531879.062, "dur": 6.239, + "args": { + "External id": 230379,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115531892.430, "dur": 6.281, + "args": { + "External id": 230380,"Record function id": 0, "Sequence number": 2757904, "Fwd thread id": 1, "Ev Idx": 491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115531893.489, "dur": 3.949, + "args": { + "External id": 230381,"Sequence number": 2757904, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 492 + } + }, + { + "ph": "f", "id": 52, "pid": 4183440, "tid": 31337, "ts": 667115531893.489, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115531895.101, "dur": 2.164, + "args": { + "External id": 230382,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115531896.265, "dur": 0.898, + "args": { + "External id": 230383,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115531901.807, "dur": 7.439, + "args": { + "External id": 230384,"Record function id": 0, "Sequence number": 2757903, "Fwd thread id": 1, "Ev Idx": 495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115531903.976, "dur": 3.456, + "args": { + "External id": 230385,"Sequence number": 2757903, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 496 + } + }, + { + "ph": "f", "id": 53, "pid": 4183440, "tid": 31337, "ts": 667115531903.976, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115531905.238, "dur": 2.039, + "args": { + "External id": 230386,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115531906.352, "dur": 0.797, + "args": { + "External id": 230387,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115531912.783, "dur": 6.676, + "args": { + "External id": 230388,"Record function id": 0, "Sequence number": 2757902, "Fwd thread id": 1, "Ev Idx": 499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115531913.977, "dur": 3.316, + "args": { + "External id": 230389,"Sequence number": 2757902, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 500 + } + }, + { + "ph": "f", "id": 54, "pid": 4183440, "tid": 31337, "ts": 667115531913.977, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115531915.264, "dur": 1.879, + "args": { + "External id": 230390,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115531916.038, "dur": 1.013, + "args": { + "External id": 230391,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115531922.894, "dur": 170.657, + "args": { + "External id": 230392,"Record function id": 0, "Sequence number": 2757901, "Fwd thread id": 1, "Ev Idx": 503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115531923.657, "dur": 163.364, + "args": { + "External id": 230393,"Sequence number": 2757901, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 504 + } + }, + { + "ph": "f", "id": 55, "pid": 4183440, "tid": 31337, "ts": 667115531923.657, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115531928.984, "dur": 6.787, + "args": { + "External id": 230394,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115531930.704, "dur": 4.459, + "args": { + "External id": 230395,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[65536, 1024], [], []], "Ev Idx": 506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115531933.329, "dur": 1.508, + "args": { + "External id": 230396,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115531937.344, "dur": 75.924, + "args": { + "External id": 230397,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024]], "Ev Idx": 508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115532014.533, "dur": 6.990, + "args": { + "External id": 230398,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115532015.539, "dur": 5.086, + "args": { + "External id": 230399,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115532019.296, "dur": 1.208, + "args": { + "External id": 230400,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115532042.235, "dur": 3.432, + "args": { + "External id": 230401,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115532043.317, "dur": 1.863, + "args": { + "External id": 230402,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115532044.718, "dur": 0.399, + "args": { + "External id": 230403,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115532046.429, "dur": 39.653, + "args": { + "External id": 230404,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532098.297, "dur": 6.976, + "args": { + "External id": 230405,"Record function id": 0, "Sequence number": 2757900, "Fwd thread id": 1, "Ev Idx": 516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532099.165, "dur": 3.898, + "args": { + "External id": 230406,"Sequence number": 2757900, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 517 + } + }, + { + "ph": "f", "id": 56, "pid": 4183440, "tid": 31337, "ts": 667115532099.165, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115532100.782, "dur": 2.148, + "args": { + "External id": 230407,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115532101.689, "dur": 1.083, + "args": { + "External id": 230408,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532108.475, "dur": 8.067, + "args": { + "External id": 230409,"Record function id": 0, "Sequence number": 2757899, "Fwd thread id": 1, "Ev Idx": 520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532110.774, "dur": 4.021, + "args": { + "External id": 230410,"Sequence number": 2757899, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 521 + } + }, + { + "ph": "f", "id": 57, "pid": 4183440, "tid": 31337, "ts": 667115532110.774, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115532111.470, "dur": 3.132, + "args": { + "External id": 230411,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115532112.049, "dur": 2.115, + "args": { + "External id": 230412,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115532113.540, "dur": 0.479, + "args": { + "External id": 230413,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115532122.104, "dur": 9.092, + "args": { + "External id": 230414,"Record function id": 0, "Ev Idx": 525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115532124.060, "dur": 6.188, + "args": { + "External id": 230415,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115532126.468, "dur": 3.426, + "args": { + "External id": 230416,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115532127.390, "dur": 2.373, + "args": { + "External id": 230417,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532136.704, "dur": 8.390, + "args": { + "External id": 230418,"Record function id": 0, "Sequence number": 2757898, "Fwd thread id": 1, "Ev Idx": 529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532137.974, "dur": 4.990, + "args": { + "External id": 230419,"Sequence number": 2757898, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 530 + } + }, + { + "ph": "f", "id": 58, "pid": 4183440, "tid": 31337, "ts": 667115532137.974, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115532139.227, "dur": 3.588, + "args": { + "External id": 230420,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115532141.805, "dur": 0.882, + "args": { + "External id": 230421,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532148.433, "dur": 91.117, + "args": { + "External id": 230422,"Record function id": 0, "Sequence number": 2757897, "Fwd thread id": 1, "Ev Idx": 533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532149.059, "dur": 85.887, + "args": { + "External id": 230423,"Sequence number": 2757897, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 534 + } + }, + { + "ph": "f", "id": 59, "pid": 4183440, "tid": 31337, "ts": 667115532149.059, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115532151.836, "dur": 2.735, + "args": { + "External id": 230424,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115532152.267, "dur": 1.860, + "args": { + "External id": 230425,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[65536, 1024], [], []], "Ev Idx": 536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115532153.689, "dur": 0.295, + "args": { + "External id": 230426,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115532157.580, "dur": 33.251, + "args": { + "External id": 230427,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024]], "Ev Idx": 538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115532192.133, "dur": 3.342, + "args": { + "External id": 230428,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115532192.658, "dur": 2.273, + "args": { + "External id": 230429,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115532194.258, "dur": 0.558, + "args": { + "External id": 230430,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115532196.622, "dur": 4.841, + "args": { + "External id": 230431,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115532197.260, "dur": 3.757, + "args": { + "External id": 230432,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115532198.627, "dur": 2.290, + "args": { + "External id": 230433,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115532203.918, "dur": 30.239, + "args": { + "External id": 230434,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532243.709, "dur": 30.147, + "args": { + "External id": 230435,"Record function id": 0, "Sequence number": 2757896, "Fwd thread id": 1, "Ev Idx": 546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532244.520, "dur": 3.568, + "args": { + "External id": 230436,"Sequence number": 2757896, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 547 + } + }, + { + "ph": "f", "id": 60, "pid": 4183440, "tid": 31337, "ts": 667115532244.520, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115532246.090, "dur": 1.864, + "args": { + "External id": 230437,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115532246.918, "dur": 0.898, + "args": { + "External id": 230438,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 4183440, "tid": 31337, + "ts": 667115532251.247, "dur": 20.692, + "args": { + "External id": 230439,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532277.701, "dur": 8.846, + "args": { + "External id": 230440,"Record function id": 0, "Sequence number": 2757895, "Fwd thread id": 1, "Ev Idx": 551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532278.678, "dur": 6.003, + "args": { + "External id": 230441,"Sequence number": 2757895, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 552 + } + }, + { + "ph": "f", "id": 61, "pid": 4183440, "tid": 31337, "ts": 667115532278.678, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115532279.706, "dur": 4.788, + "args": { + "External id": 230442,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115532281.774, "dur": 2.202, + "args": { + "External id": 230443,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115532283.403, "dur": 0.460, + "args": { + "External id": 230444,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115532290.507, "dur": 5.346, + "args": { + "External id": 230445,"Record function id": 0, "Ev Idx": 556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115532292.167, "dur": 3.090, + "args": { + "External id": 230446,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115532293.137, "dur": 1.797, + "args": { + "External id": 230447,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115532293.809, "dur": 1.032, + "args": { + "External id": 230448,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532299.199, "dur": 5.911, + "args": { + "External id": 230449,"Record function id": 0, "Sequence number": 2757894, "Fwd thread id": 1, "Ev Idx": 560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532300.507, "dur": 2.821, + "args": { + "External id": 230450,"Sequence number": 2757894, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 561 + } + }, + { + "ph": "f", "id": 62, "pid": 4183440, "tid": 31337, "ts": 667115532300.507, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115532301.400, "dur": 1.782, + "args": { + "External id": 230451,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115532302.260, "dur": 0.793, + "args": { + "External id": 230452,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532310.090, "dur": 93.553, + "args": { + "External id": 230453,"Record function id": 0, "Sequence number": 2757893, "Fwd thread id": 1, "Ev Idx": 564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532310.936, "dur": 86.641, + "args": { + "External id": 230454,"Sequence number": 2757893, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 565 + } + }, + { + "ph": "f", "id": 63, "pid": 4183440, "tid": 31337, "ts": 667115532310.936, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115532313.280, "dur": 2.755, + "args": { + "External id": 230455,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115532313.705, "dur": 1.891, + "args": { + "External id": 230456,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[65536, 1024], [], []], "Ev Idx": 567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115532315.061, "dur": 0.409, + "args": { + "External id": 230457,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115532316.707, "dur": 37.998, + "args": { + "External id": 230458,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024]], "Ev Idx": 569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115532355.750, "dur": 5.723, + "args": { + "External id": 230459,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115532358.232, "dur": 2.620, + "args": { + "External id": 230460,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115532360.227, "dur": 0.471, + "args": { + "External id": 230461,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115532362.672, "dur": 3.153, + "args": { + "External id": 230462,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115532363.490, "dur": 1.891, + "args": { + "External id": 230463,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115532364.909, "dur": 0.374, + "args": { + "External id": 230464,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115532366.463, "dur": 30.418, + "args": { + "External id": 230465,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532408.106, "dur": 24.585, + "args": { + "External id": 230466,"Record function id": 0, "Sequence number": 2757892, "Fwd thread id": 1, "Ev Idx": 577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532410.658, "dur": 3.750, + "args": { + "External id": 230467,"Sequence number": 2757892, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 578 + } + }, + { + "ph": "f", "id": 64, "pid": 4183440, "tid": 31337, "ts": 667115532410.658, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115532412.374, "dur": 1.858, + "args": { + "External id": 230468,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115532413.201, "dur": 0.897, + "args": { + "External id": 230469,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 31337, + "ts": 667115532416.695, "dur": 14.081, + "args": { + "External id": 230470,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532436.159, "dur": 11.163, + "args": { + "External id": 230471,"Record function id": 0, "Sequence number": 2757891, "Fwd thread id": 1, "Ev Idx": 582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532437.209, "dur": 7.793, + "args": { + "External id": 230472,"Sequence number": 2757891, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 583 + } + }, + { + "ph": "f", "id": 65, "pid": 4183440, "tid": 31337, "ts": 667115532437.209, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115532437.764, "dur": 7.026, + "args": { + "External id": 230473,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115532440.117, "dur": 4.188, + "args": { + "External id": 230474,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115532443.778, "dur": 0.402, + "args": { + "External id": 230475,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115532451.416, "dur": 5.450, + "args": { + "External id": 230476,"Record function id": 0, "Ev Idx": 587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115532453.214, "dur": 3.093, + "args": { + "External id": 230477,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115532454.085, "dur": 1.919, + "args": { + "External id": 230478,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115532454.786, "dur": 1.085, + "args": { + "External id": 230479,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115532461.325, "dur": 418.101, + "args": { + "External id": 230480,"Record function id": 0, "Sequence number": 2757890, "Fwd thread id": 1, "Ev Idx": 591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115532462.705, "dur": 379.760, + "args": { + "External id": 230481,"Sequence number": 2757890, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 592 + } + }, + { + "ph": "f", "id": 66, "pid": 4183440, "tid": 31337, "ts": 667115532462.705, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115532489.119, "dur": 20.765, + "args": { + "External id": 230482,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115532489.960, "dur": 19.471, + "args": { + "External id": 230483,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115532525.445, "dur": 6.310, + "args": { + "External id": 230484,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115532542.481, "dur": 4.876, + "args": { + "External id": 230485,"Record function id": 0, "Concrete Inputs": ["[132, 1024]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115532738.500, "dur": 2.967, + "args": { + "External id": 230486,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 1024]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[132, 1024], []], "Ev Idx": 597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 31337, + "ts": 667115532746.243, "dur": 37.272, + "args": { + "External id": 230487,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[135168, 1024, 1], [], [], []], "Input Dims": [[1, 132, 1024], [], [], []], "Ev Idx": 598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115532758.175, "dur": 0.793, + "args": { + "External id": 230488,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 1024]", "[1024, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1, 1024], [], [], []], "Ev Idx": 599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115532789.334, "dur": 28.349, + "args": { + "External id": 230489,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[1, 1024], [], [], [], [], []], "Ev Idx": 600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115532791.318, "dur": 26.171, + "args": { + "External id": 230490,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], [], []], "Input Dims": [[1, 1024], [], [], [], [], [], []], "Ev Idx": 601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115532795.880, "dur": 4.083, + "args": { + "External id": 230491,"Record function id": 0, "Concrete Inputs": ["[1, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115532801.511, "dur": 15.333, + "args": { + "External id": 230492,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[1, 1024], [1, 1024], []], "Ev Idx": 603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 31337, + "ts": 667115532822.782, "dur": 4.685, + "args": { + "External id": 230493,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1]], "Input Dims": [[1, 1024], [1024]], "Ev Idx": 604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115532825.940, "dur": 1.379, + "args": { + "External id": 230494,"Record function id": 0, "Concrete Inputs": ["", "[1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[1, 1024], []], "Ev Idx": 605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115532833.420, "dur": 2.559, + "args": { + "External id": 230495,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115532834.735, "dur": 1.146, + "args": { + "External id": 230496,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 4183440, "tid": 31337, + "ts": 667115532854.593, "dur": 17.883, + "args": { + "External id": 230497,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115532893.341, "dur": 9.458, + "args": { + "External id": 230498,"Record function id": 0, "Ev Idx": 609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115532895.659, "dur": 6.304, + "args": { + "External id": 230499,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115532897.851, "dur": 3.001, + "args": { + "External id": 230500,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115532898.736, "dur": 1.968, + "args": { + "External id": 230501,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532908.953, "dur": 6.889, + "args": { + "External id": 230502,"Record function id": 0, "Sequence number": 2757889, "Fwd thread id": 1, "Ev Idx": 613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115532910.719, "dur": 1.349, + "args": { + "External id": 230503,"Sequence number": 2757889, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 614 + } + }, + { + "ph": "f", "id": 67, "pid": 4183440, "tid": 31337, "ts": 667115532910.719, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115532919.798, "dur": 410.170, + "args": { + "External id": 230504,"Record function id": 0, "Sequence number": 2757888, "Fwd thread id": 1, "Ev Idx": 615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115532921.811, "dur": 398.220, + "args": { + "External id": 230505,"Sequence number": 2757888, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 616 + } + }, + { + "ph": "f", "id": 68, "pid": 4183440, "tid": 31337, "ts": 667115532921.811, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115532952.463, "dur": 9.134, + "args": { + "External id": 230506,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 4183440, "tid": 31337, + "ts": 667115532958.075, "dur": 3.253, + "args": { + "External id": 230507,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]", "[4096, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[16777216, 4096, 1], [], []], "Input Dims": [[16, 4096, 1024], [], []], "Ev Idx": 618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115532964.731, "dur": 7.567, + "args": { + "External id": 230508,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115532966.575, "dur": 5.083, + "args": { + "External id": 230509,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2816, 1], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115532968.696, "dur": 2.759, + "args": { + "External id": 230510,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 31337, + "ts": 667115532978.028, "dur": 102.317, + "args": { + "External id": 230511,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [1, 2816], []], "Input Dims": [[65536, 1024], [2816, 1024], []], "Ev Idx": 622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115532979.102, "dur": 2.864, + "args": { + "External id": 230512,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2816]], "Input Dims": [[2816, 1024]], "Ev Idx": 623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115532979.681, "dur": 1.813, + "args": { + "External id": 230513,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2816], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115532981.072, "dur": 0.331, + "args": { + "External id": 230514,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[2816, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2816], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 31337, + "ts": 667115532983.292, "dur": 96.481, + "args": { + "External id": 230515,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816]], "Ev Idx": 626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115532984.879, "dur": 93.990, + "args": { + "External id": 230516,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816]], "Ev Idx": 627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 31337, + "ts": 667115533083.878, "dur": 4.913, + "args": { + "External id": 230517,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [11534336, 2816, 1]], "Input Dims": [[65536, 2816], [16, 4096, 2816]], "Ev Idx": 628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115533087.239, "dur": 1.444, + "args": { + "External id": 230518,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1], []], "Input Dims": [[65536, 2816], []], "Ev Idx": 629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115533121.185, "dur": 5.391, + "args": { + "External id": 230519,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2816]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115533128.412, "dur": 2.185, + "args": { + "External id": 230520,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2816]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115533131.647, "dur": 1.755, + "args": { + "External id": 230521,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2816]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115533163.509, "dur": 2.327, + "args": { + "External id": 230522,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115533164.362, "dur": 1.275, + "args": { + "External id": 230523,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 4183440, "tid": 31337, + "ts": 667115533189.659, "dur": 111.259, + "args": { + "External id": 230524,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[4096, 1], [2816, 1]], []], "Input Dims": [[], [[65536, 1024], [65536, 2816]], []], "Ev Idx": 635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 31337, + "ts": 667115533194.700, "dur": 7.385, + "args": { + "External id": 230525,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115533198.701, "dur": 2.691, + "args": { + "External id": 230526,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024, 1]", "[4096, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115533203.945, "dur": 6.546, + "args": { + "External id": 230527,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1, 1], []], "Input Dims": [[65536, 1024, 1], []], "Ev Idx": 638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115533209.326, "dur": 0.556, + "args": { + "External id": 230528,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1, 65536]", "[1, 1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1, 1], [], [], []], "Input Dims": [[65536, 1024, 1], [], [], []], "Ev Idx": 639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 31337, + "ts": 667115533211.824, "dur": 3.018, + "args": { + "External id": 230529,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], []], "Input Dims": [[65536, 2816], []], "Ev Idx": 640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115533213.796, "dur": 0.704, + "args": { + "External id": 230530,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816, 1]", "[2816, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[65536, 2816], [], [], []], "Ev Idx": 641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115533215.953, "dur": 3.084, + "args": { + "External id": 230531,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1, 1], []], "Input Dims": [[65536, 2816, 1], []], "Ev Idx": 642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115533218.189, "dur": 0.437, + "args": { + "External id": 230532,"Record function id": 0, "Concrete Inputs": ["", "[1, 2816, 65536]", "[1, 1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1, 1], [], [], []], "Input Dims": [[65536, 2816, 1], [], [], []], "Ev Idx": 643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115533222.712, "dur": 3.009, + "args": { + "External id": 230533,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 4096], []], "Input Dims": [[1024, 1, 65536], []], "Ev Idx": 644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115533224.688, "dur": 0.730, + "args": { + "External id": 230534,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536, 1]", "[1, 4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 4096], [], [], []], "Input Dims": [[1024, 1, 65536], [], [], []], "Ev Idx": 645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115533228.986, "dur": 6.044, + "args": { + "External id": 230535,"Record function id": 0, "Concrete Inputs": ["", "[1, 1024, 65536]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 4096, 1], []], "Input Dims": [[1024, 65536, 1], []], "Ev Idx": 646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 4183440, "tid": 31337, + "ts": 667115533233.244, "dur": 1.605, + "args": { + "External id": 230536,"Record function id": 0, "Concrete Inputs": ["", "[1, 1024, 65536]", "[1024, 1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 4096, 1], [], []], "Input Dims": [[1024, 65536, 1], [], []], "Ev Idx": 647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115533235.847, "dur": 2.905, + "args": { + "External id": 230537,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 2816], []], "Input Dims": [[1, 2816, 65536], []], "Ev Idx": 648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115533237.918, "dur": 0.512, + "args": { + "External id": 230538,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816, 1]", "[2816, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 2816], [], [], []], "Input Dims": [[1, 2816, 65536], [], [], []], "Ev Idx": 649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115533239.867, "dur": 3.680, + "args": { + "External id": 230539,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1, 1], []], "Input Dims": [[65536, 2816, 1], []], "Ev Idx": 650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115533241.269, "dur": 2.189, + "args": { + "External id": 230540,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1, 1], []], "Input Dims": [[65536, 2816, 1], []], "Ev Idx": 651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115533244.974, "dur": 45.033, + "args": { + "External id": 230541,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1, 4096], [184549376, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816]], "Ev Idx": 652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115533291.878, "dur": 0.783, + "args": { + "External id": 230542,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2883584, 2816, 1], []], "Input Dims": [[1, 1024, 2816], []], "Ev Idx": 653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115533293.717, "dur": 2.944, + "args": { + "External id": 230543,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 2816, 1], []], "Input Dims": [[1024, 1, 2816], []], "Ev Idx": 654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115533295.673, "dur": 0.535, + "args": { + "External id": 230544,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816, 1]", "[2816, 1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 2816, 1], [], [], []], "Input Dims": [[1024, 1, 2816], [], [], []], "Ev Idx": 655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115533298.798, "dur": 1.061, + "args": { + "External id": 230545,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1, 2816], []], "Input Dims": [[1024, 2816, 1], []], "Ev Idx": 656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115533338.898, "dur": 8.557, + "args": { + "External id": 230546,"Record function id": 0, "Ev Idx": 657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115533341.169, "dur": 5.552, + "args": { + "External id": 230547,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115533343.058, "dur": 2.857, + "args": { + "External id": 230548,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115533344.158, "dur": 1.641, + "args": { + "External id": 230549,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115533351.474, "dur": 7.111, + "args": { + "External id": 230550,"Record function id": 0, "Sequence number": 2757887, "Fwd thread id": 1, "Ev Idx": 661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115533352.933, "dur": 3.918, + "args": { + "External id": 230551,"Sequence number": 2757887, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[11534336, 2816, 1]], "Input Dims": [[16, 4096, 2816]], "Ev Idx": 662 + } + }, + { + "ph": "f", "id": 69, "pid": 4183440, "tid": 31337, "ts": 667115533352.933, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115533354.641, "dur": 2.048, + "args": { + "External id": 230552,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115533355.517, "dur": 1.042, + "args": { + "External id": 230553,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115533362.335, "dur": 103.168, + "args": { + "External id": 230554,"Record function id": 0, "Sequence number": 2757886, "Fwd thread id": 1, "Ev Idx": 665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115533363.224, "dur": 96.335, + "args": { + "External id": 230555,"Sequence number": 2757886, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[65536, 2816]], "Ev Idx": 666 + } + }, + { + "ph": "f", "id": 70, "pid": 4183440, "tid": 31337, "ts": 667115533363.224, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115533367.858, "dur": 4.166, + "args": { + "External id": 230556,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[65536, 2816]], "Ev Idx": 667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115533369.295, "dur": 2.206, + "args": { + "External id": 230557,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2816, 1], [], []], "Input Dims": [[65536, 2816], [], []], "Ev Idx": 668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115533370.840, "dur": 0.491, + "args": { + "External id": 230558,"Record function id": 0, "Concrete Inputs": ["", "[2816, 65536]", "[1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[65536, 2816], [], [], []], "Ev Idx": 669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115533373.146, "dur": 32.429, + "args": { + "External id": 230559,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024]], "Ev Idx": 670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115533406.671, "dur": 5.674, + "args": { + "External id": 230560,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115533407.491, "dur": 4.214, + "args": { + "External id": 230561,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115533410.505, "dur": 1.058, + "args": { + "External id": 230562,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115533413.756, "dur": 5.471, + "args": { + "External id": 230563,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115533414.718, "dur": 3.978, + "args": { + "External id": 230564,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115533416.583, "dur": 2.016, + "args": { + "External id": 230565,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115533419.771, "dur": 38.913, + "args": { + "External id": 230566,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024]], "Ev Idx": 677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115533469.944, "dur": 7.168, + "args": { + "External id": 230567,"Record function id": 0, "Sequence number": 2757885, "Fwd thread id": 1, "Ev Idx": 678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115533470.907, "dur": 4.793, + "args": { + "External id": 230568,"Sequence number": 2757885, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 679 + } + }, + { + "ph": "f", "id": 71, "pid": 4183440, "tid": 31337, "ts": 667115533470.907, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115533472.760, "dur": 2.803, + "args": { + "External id": 230569,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115533473.972, "dur": 1.471, + "args": { + "External id": 230570,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115533480.859, "dur": 31.379, + "args": { + "External id": 230571,"Record function id": 0, "Sequence number": 2757884, "Fwd thread id": 1, "Ev Idx": 682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115533483.848, "dur": 4.738, + "args": { + "External id": 230572,"Sequence number": 2757884, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 683 + } + }, + { + "ph": "f", "id": 72, "pid": 4183440, "tid": 31337, "ts": 667115533483.848, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115533485.092, "dur": 3.300, + "args": { + "External id": 230573,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115533485.804, "dur": 2.121, + "args": { + "External id": 230574,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115533487.323, "dur": 0.480, + "args": { + "External id": 230575,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115533518.863, "dur": 7.568, + "args": { + "External id": 230576,"Record function id": 0, "Ev Idx": 687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115533521.256, "dur": 4.601, + "args": { + "External id": 230577,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115533522.820, "dur": 2.667, + "args": { + "External id": 230578,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115533523.877, "dur": 1.528, + "args": { + "External id": 230579,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115533529.613, "dur": 9.231, + "args": { + "External id": 230580,"Record function id": 0, "Sequence number": 2757883, "Fwd thread id": 1, "Ev Idx": 691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115533531.191, "dur": 5.465, + "args": { + "External id": 230581,"Sequence number": 2757883, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[11534336, 2816, 1]], "Input Dims": [[16, 4096, 2816]], "Ev Idx": 692 + } + }, + { + "ph": "f", "id": 73, "pid": 4183440, "tid": 31337, "ts": 667115533531.191, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115533532.364, "dur": 4.114, + "args": { + "External id": 230582,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115533535.163, "dur": 1.160, + "args": { + "External id": 230583,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115533541.986, "dur": 101.527, + "args": { + "External id": 230584,"Record function id": 0, "Sequence number": 2757882, "Fwd thread id": 1, "Ev Idx": 695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115533542.729, "dur": 92.702, + "args": { + "External id": 230585,"Sequence number": 2757882, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[65536, 2816]], "Ev Idx": 696 + } + }, + { + "ph": "f", "id": 74, "pid": 4183440, "tid": 31337, "ts": 667115533542.729, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115533545.156, "dur": 6.718, + "args": { + "External id": 230586,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[65536, 2816]], "Ev Idx": 697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115533545.856, "dur": 5.529, + "args": { + "External id": 230587,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2816, 1], [], []], "Input Dims": [[65536, 2816], [], []], "Ev Idx": 698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115533550.486, "dur": 0.740, + "args": { + "External id": 230588,"Record function id": 0, "Concrete Inputs": ["", "[2816, 65536]", "[1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[65536, 2816], [], [], []], "Ev Idx": 699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115533554.342, "dur": 32.405, + "args": { + "External id": 230589,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024]], "Ev Idx": 700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115533587.742, "dur": 7.486, + "args": { + "External id": 230590,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115533588.390, "dur": 6.158, + "args": { + "External id": 230591,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115533590.473, "dur": 3.936, + "args": { + "External id": 230592,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115533596.489, "dur": 4.868, + "args": { + "External id": 230593,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115533597.339, "dur": 3.567, + "args": { + "External id": 230594,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115533600.212, "dur": 0.630, + "args": { + "External id": 230595,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115533601.753, "dur": 32.977, + "args": { + "External id": 230596,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024]], "Ev Idx": 707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115533647.971, "dur": 71.879, + "args": { + "External id": 230597,"Record function id": 0, "Sequence number": 2757881, "Fwd thread id": 1, "Ev Idx": 708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115533648.708, "dur": 41.095, + "args": { + "External id": 230598,"Sequence number": 2757881, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 709 + } + }, + { + "ph": "f", "id": 75, "pid": 4183440, "tid": 31337, "ts": 667115533648.708, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115533650.245, "dur": 39.340, + "args": { + "External id": 230599,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115533687.462, "dur": 1.796, + "args": { + "External id": 230600,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 4183440, "tid": 31337, + "ts": 667115533693.801, "dur": 23.102, + "args": { + "External id": 230601,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115533725.475, "dur": 9.733, + "args": { + "External id": 230602,"Record function id": 0, "Sequence number": 2757880, "Fwd thread id": 1, "Ev Idx": 713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115533726.692, "dur": 6.542, + "args": { + "External id": 230603,"Sequence number": 2757880, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 714 + } + }, + { + "ph": "f", "id": 76, "pid": 4183440, "tid": 31337, "ts": 667115533726.692, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115533727.574, "dur": 5.453, + "args": { + "External id": 230604,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115533728.728, "dur": 3.762, + "args": { + "External id": 230605,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115533731.767, "dur": 0.580, + "args": { + "External id": 230606,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115533739.463, "dur": 6.816, + "args": { + "External id": 230607,"Record function id": 0, "Ev Idx": 718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115533741.526, "dur": 4.211, + "args": { + "External id": 230608,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115533743.013, "dur": 2.375, + "args": { + "External id": 230609,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115533743.903, "dur": 1.395, + "args": { + "External id": 230610,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115533752.276, "dur": 399.078, + "args": { + "External id": 230611,"Record function id": 0, "Sequence number": 2757879, "Fwd thread id": 1, "Ev Idx": 722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115533754.002, "dur": 364.209, + "args": { + "External id": 230612,"Sequence number": 2757879, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [16777216, 4096, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 723 + } + }, + { + "ph": "f", "id": 77, "pid": 4183440, "tid": 31337, "ts": 667115533754.002, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183440, "tid": 31337, + "ts": 667115533777.523, "dur": 35.399, + "args": { + "External id": 230613,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 31337, + "ts": 667115533778.988, "dur": 33.726, + "args": { + "External id": 230614,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115533782.085, "dur": 6.276, + "args": { + "External id": 230615,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], [], [], []], "Ev Idx": 726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115533784.930, "dur": 3.042, + "args": { + "External id": 230616,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 1024]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115533789.762, "dur": 22.439, + "args": { + "External id": 230617,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115533822.936, "dur": 5.720, + "args": { + "External id": 230618,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115533825.816, "dur": 2.698, + "args": { + "External id": 230619,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115533832.529, "dur": 1.777, + "args": { + "External id": 230620,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115533833.520, "dur": 0.695, + "args": { + "External id": 230621,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115533846.200, "dur": 2.118, + "args": { + "External id": 230622,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115533859.594, "dur": 3.407, + "args": { + "External id": 230623,"Record function id": 0, "Concrete Inputs": ["[132, 1024]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115534016.475, "dur": 2.093, + "args": { + "External id": 230624,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 1024]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[132, 1024], []], "Ev Idx": 735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 31337, + "ts": 667115534022.627, "dur": 31.465, + "args": { + "External id": 230625,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[135168, 1024, 1], [], [], []], "Input Dims": [[1, 132, 1024], [], [], []], "Ev Idx": 736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115534031.152, "dur": 0.869, + "args": { + "External id": 230626,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 1024]", "[1024, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1, 1024], [], [], []], "Ev Idx": 737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115534059.353, "dur": 27.262, + "args": { + "External id": 230627,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[1, 1024], [], [], [], [], []], "Ev Idx": 738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115534061.224, "dur": 25.187, + "args": { + "External id": 230628,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], [], []], "Input Dims": [[1, 1024], [], [], [], [], [], []], "Ev Idx": 739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115534065.599, "dur": 3.752, + "args": { + "External id": 230629,"Record function id": 0, "Concrete Inputs": ["[1, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115534070.537, "dur": 15.340, + "args": { + "External id": 230630,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[1, 1024], [1, 1024], []], "Ev Idx": 741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 31337, + "ts": 667115534091.348, "dur": 4.437, + "args": { + "External id": 230631,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1]], "Input Dims": [[1, 1024], [1024]], "Ev Idx": 742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115534094.534, "dur": 1.144, + "args": { + "External id": 230632,"Record function id": 0, "Concrete Inputs": ["", "[1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[1, 1024], []], "Ev Idx": 743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115534101.543, "dur": 4.180, + "args": { + "External id": 230633,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115534102.836, "dur": 2.716, + "args": { + "External id": 230634,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115534107.771, "dur": 2.280, + "args": { + "External id": 230635,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115534108.984, "dur": 0.980, + "args": { + "External id": 230636,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 31337, + "ts": 667115534131.308, "dur": 18.462, + "args": { + "External id": 230637,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115534161.161, "dur": 10.038, + "args": { + "External id": 230638,"Record function id": 0, "Ev Idx": 749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115534163.547, "dur": 6.863, + "args": { + "External id": 230639,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115534165.274, "dur": 4.105, + "args": { + "External id": 230640,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115534167.743, "dur": 1.547, + "args": { + "External id": 230641,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115534175.103, "dur": 8.013, + "args": { + "External id": 230642,"Record function id": 0, "Sequence number": 2757878, "Fwd thread id": 1, "Ev Idx": 753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115534176.461, "dur": 3.996, + "args": { + "External id": 230643,"Sequence number": 2757878, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 754 + } + }, + { + "ph": "f", "id": 78, "pid": 4183440, "tid": 31337, "ts": 667115534176.461, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115534178.076, "dur": 2.199, + "args": { + "External id": 230644,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115534179.042, "dur": 1.088, + "args": { + "External id": 230645,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115534186.468, "dur": 131.393, + "args": { + "External id": 230646,"Record function id": 0, "Sequence number": 2757877, "Fwd thread id": 1, "Ev Idx": 757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115534187.192, "dur": 124.509, + "args": { + "External id": 230647,"Sequence number": 2757877, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 758 + } + }, + { + "ph": "f", "id": 79, "pid": 4183440, "tid": 31337, "ts": 667115534187.192, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115534190.352, "dur": 6.941, + "args": { + "External id": 230648,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115534193.672, "dur": 3.096, + "args": { + "External id": 230649,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[65536, 1024], [], []], "Ev Idx": 760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115534195.677, "dur": 0.906, + "args": { + "External id": 230650,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115534198.357, "dur": 65.801, + "args": { + "External id": 230651,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024]], "Ev Idx": 762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115534265.467, "dur": 5.374, + "args": { + "External id": 230652,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115534266.100, "dur": 4.095, + "args": { + "External id": 230653,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115534267.692, "dur": 2.363, + "args": { + "External id": 230654,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115534273.929, "dur": 3.473, + "args": { + "External id": 230655,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115534274.842, "dur": 2.084, + "args": { + "External id": 230656,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115534276.171, "dur": 0.640, + "args": { + "External id": 230657,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115534277.840, "dur": 33.103, + "args": { + "External id": 230658,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115534322.657, "dur": 9.242, + "args": { + "External id": 230659,"Record function id": 0, "Sequence number": 2757876, "Fwd thread id": 1, "Ev Idx": 770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115534323.571, "dur": 6.330, + "args": { + "External id": 230660,"Sequence number": 2757876, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 771 + } + }, + { + "ph": "f", "id": 80, "pid": 4183440, "tid": 31337, "ts": 667115534323.571, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115534325.471, "dur": 4.270, + "args": { + "External id": 230661,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115534326.454, "dur": 3.150, + "args": { + "External id": 230662,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115534335.111, "dur": 8.947, + "args": { + "External id": 230663,"Record function id": 0, "Sequence number": 2757875, "Fwd thread id": 1, "Ev Idx": 774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115534338.138, "dur": 4.261, + "args": { + "External id": 230664,"Sequence number": 2757875, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 775 + } + }, + { + "ph": "f", "id": 81, "pid": 4183440, "tid": 31337, "ts": 667115534338.138, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115534338.884, "dur": 3.308, + "args": { + "External id": 230665,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115534339.539, "dur": 2.180, + "args": { + "External id": 230666,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115534341.180, "dur": 0.418, + "args": { + "External id": 230667,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115534347.921, "dur": 5.512, + "args": { + "External id": 230668,"Record function id": 0, "Ev Idx": 779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115534349.598, "dur": 3.284, + "args": { + "External id": 230669,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115534350.709, "dur": 1.924, + "args": { + "External id": 230670,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115534351.532, "dur": 1.009, + "args": { + "External id": 230671,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115534356.500, "dur": 7.812, + "args": { + "External id": 230672,"Record function id": 0, "Sequence number": 2757874, "Fwd thread id": 1, "Ev Idx": 783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115534357.341, "dur": 5.120, + "args": { + "External id": 230673,"Sequence number": 2757874, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 784 + } + }, + { + "ph": "f", "id": 82, "pid": 4183440, "tid": 31337, "ts": 667115534357.341, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115534360.247, "dur": 2.067, + "args": { + "External id": 230674,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115534360.809, "dur": 1.348, + "args": { + "External id": 230675,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 4183440, "tid": 31337, + "ts": 667115534368.244, "dur": 333.486, + "args": { + "External id": 230676,"Record function id": 0, "Sequence number": 2757873, "Fwd thread id": 1, "Ev Idx": 787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 4183440, "tid": 31337, + "ts": 667115534370.006, "dur": 275.238, + "args": { + "External id": 230677,"Sequence number": 2757873, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 788 + } + }, + { + "ph": "f", "id": 83, "pid": 4183440, "tid": 31337, "ts": 667115534370.006, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115534384.339, "dur": 6.255, + "args": { + "External id": 230678,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115534387.237, "dur": 2.986, + "args": { + "External id": 230679,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115534392.393, "dur": 3.683, + "args": { + "External id": 230680,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115534393.837, "dur": 2.012, + "args": { + "External id": 230681,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115534397.755, "dur": 5.168, + "args": { + "External id": 230682,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115534399.608, "dur": 3.135, + "args": { + "External id": 230683,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115534425.439, "dur": 194.226, + "args": { + "External id": 230684,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115534523.548, "dur": 4.426, + "args": { + "External id": 230685,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115534530.058, "dur": 4.170, + "args": { + "External id": 230686,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 4183440, "tid": 31337, + "ts": 667115534632.365, "dur": 4.001, + "args": { + "External id": 230687,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 4183440, "tid": 31337, + "ts": 667115534639.049, "dur": 0.795, + "args": { + "External id": 230688,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 4183440, "tid": 31337, + "ts": 667115534641.772, "dur": 0.805, + "args": { + "External id": 230689,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115534713.383, "dur": 227.873, + "args": { + "External id": 230690,"Record function id": 0, "Sequence number": 2757872, "Fwd thread id": 1, "Ev Idx": 801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115534715.541, "dur": 218.507, + "args": { + "External id": 230691,"Sequence number": 2757872, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 802 + } + }, + { + "ph": "f", "id": 84, "pid": 4183440, "tid": 31337, "ts": 667115534715.541, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 31337, + "ts": 667115534735.407, "dur": 49.788, + "args": { + "External id": 230692,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115534739.297, "dur": 3.931, + "args": { + "External id": 230693,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115534744.562, "dur": 39.899, + "args": { + "External id": 230694,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], []], "Ev Idx": 805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115534795.242, "dur": 4.576, + "args": { + "External id": 230695,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115534797.238, "dur": 2.248, + "args": { + "External id": 230696,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115534948.544, "dur": 141.036, + "args": { + "External id": 230697,"Record function id": 0, "Sequence number": 2757871, "Fwd thread id": 1, "Ev Idx": 808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115534950.611, "dur": 132.928, + "args": { + "External id": 230698,"Sequence number": 2757871, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 809 + } + }, + { + "ph": "f", "id": 85, "pid": 4183440, "tid": 31337, "ts": 667115534950.611, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 31337, + "ts": 667115534961.407, "dur": 28.707, + "args": { + "External id": 230699,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115534964.067, "dur": 2.363, + "args": { + "External id": 230700,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115534967.204, "dur": 22.324, + "args": { + "External id": 230701,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], []], "Ev Idx": 812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115534997.028, "dur": 4.847, + "args": { + "External id": 230702,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115534998.802, "dur": 2.760, + "args": { + "External id": 230703,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535095.537, "dur": 16.179, + "args": { + "External id": 230704,"Record function id": 0, "Sequence number": 2757870, "Fwd thread id": 1, "Ev Idx": 815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535096.899, "dur": 12.391, + "args": { + "External id": 230705,"Sequence number": 2757870, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 816 + } + }, + { + "ph": "f", "id": 86, "pid": 4183440, "tid": 31337, "ts": 667115535096.899, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115535099.684, "dur": 9.296, + "args": { + "External id": 230706,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115535103.010, "dur": 5.805, + "args": { + "External id": 230707,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535115.431, "dur": 6.534, + "args": { + "External id": 230708,"Record function id": 0, "Sequence number": 2757869, "Fwd thread id": 1, "Ev Idx": 819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535116.217, "dur": 3.823, + "args": { + "External id": 230709,"Sequence number": 2757869, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 820 + } + }, + { + "ph": "f", "id": 87, "pid": 4183440, "tid": 31337, "ts": 667115535116.217, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115535117.810, "dur": 2.071, + "args": { + "External id": 230710,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115535118.842, "dur": 0.927, + "args": { + "External id": 230711,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535127.141, "dur": 6.534, + "args": { + "External id": 230712,"Record function id": 0, "Sequence number": 2757868, "Fwd thread id": 1, "Ev Idx": 823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535128.019, "dur": 3.847, + "args": { + "External id": 230713,"Sequence number": 2757868, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 824 + } + }, + { + "ph": "f", "id": 88, "pid": 4183440, "tid": 31337, "ts": 667115535128.019, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115535129.530, "dur": 2.211, + "args": { + "External id": 230714,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115535130.787, "dur": 0.859, + "args": { + "External id": 230715,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535137.236, "dur": 8.055, + "args": { + "External id": 230716,"Record function id": 0, "Sequence number": 2757867, "Fwd thread id": 1, "Ev Idx": 827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535138.430, "dur": 5.032, + "args": { + "External id": 230717,"Sequence number": 2757867, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 828 + } + }, + { + "ph": "f", "id": 89, "pid": 4183440, "tid": 31337, "ts": 667115535138.430, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115535139.480, "dur": 3.835, + "args": { + "External id": 230718,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115535142.342, "dur": 0.878, + "args": { + "External id": 230719,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535148.790, "dur": 209.582, + "args": { + "External id": 230720,"Record function id": 0, "Sequence number": 2757866, "Fwd thread id": 1, "Ev Idx": 831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535149.768, "dur": 199.075, + "args": { + "External id": 230721,"Sequence number": 2757866, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 832 + } + }, + { + "ph": "f", "id": 90, "pid": 4183440, "tid": 31337, "ts": 667115535149.768, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115535153.382, "dur": 6.855, + "args": { + "External id": 230722,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115535155.226, "dur": 4.381, + "args": { + "External id": 230723,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[65536, 1024], [], []], "Ev Idx": 834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115535157.621, "dur": 1.693, + "args": { + "External id": 230724,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115535163.499, "dur": 77.358, + "args": { + "External id": 230725,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024]], "Ev Idx": 836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115535242.201, "dur": 5.030, + "args": { + "External id": 230726,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115535243.070, "dur": 3.367, + "args": { + "External id": 230727,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115535245.074, "dur": 1.231, + "args": { + "External id": 230728,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115535248.708, "dur": 51.379, + "args": { + "External id": 230729,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115535249.777, "dur": 49.451, + "args": { + "External id": 230730,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115535297.970, "dur": 0.806, + "args": { + "External id": 230731,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115535301.164, "dur": 46.725, + "args": { + "External id": 230732,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535366.247, "dur": 8.841, + "args": { + "External id": 230733,"Record function id": 0, "Sequence number": 2757865, "Fwd thread id": 1, "Ev Idx": 844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535367.474, "dur": 5.661, + "args": { + "External id": 230734,"Sequence number": 2757865, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 845 + } + }, + { + "ph": "f", "id": 91, "pid": 4183440, "tid": 31337, "ts": 667115535367.474, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115535370.011, "dur": 2.989, + "args": { + "External id": 230735,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115535371.238, "dur": 1.666, + "args": { + "External id": 230736,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535378.497, "dur": 9.779, + "args": { + "External id": 230737,"Record function id": 0, "Sequence number": 2757864, "Fwd thread id": 1, "Ev Idx": 848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535379.329, "dur": 7.195, + "args": { + "External id": 230738,"Sequence number": 2757864, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 849 + } + }, + { + "ph": "f", "id": 92, "pid": 4183440, "tid": 31337, "ts": 667115535379.329, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115535380.460, "dur": 5.855, + "args": { + "External id": 230739,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115535381.395, "dur": 4.421, + "args": { + "External id": 230740,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115535385.212, "dur": 0.495, + "args": { + "External id": 230741,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115535394.243, "dur": 9.511, + "args": { + "External id": 230742,"Record function id": 0, "Ev Idx": 853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115535395.909, "dur": 7.011, + "args": { + "External id": 230743,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115535398.637, "dur": 3.946, + "args": { + "External id": 230744,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115535399.714, "dur": 2.724, + "args": { + "External id": 230745,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535407.247, "dur": 6.091, + "args": { + "External id": 230746,"Record function id": 0, "Sequence number": 2757863, "Fwd thread id": 1, "Ev Idx": 857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535408.577, "dur": 3.318, + "args": { + "External id": 230747,"Sequence number": 2757863, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 858 + } + }, + { + "ph": "f", "id": 93, "pid": 4183440, "tid": 31337, "ts": 667115535408.577, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115535409.920, "dur": 1.833, + "args": { + "External id": 230748,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115535410.969, "dur": 0.660, + "args": { + "External id": 230749,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535416.556, "dur": 112.075, + "args": { + "External id": 230750,"Record function id": 0, "Sequence number": 2757862, "Fwd thread id": 1, "Ev Idx": 861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535417.224, "dur": 104.751, + "args": { + "External id": 230751,"Sequence number": 2757862, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 862 + } + }, + { + "ph": "f", "id": 94, "pid": 4183440, "tid": 31337, "ts": 667115535417.224, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115535421.375, "dur": 3.475, + "args": { + "External id": 230752,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115535421.952, "dur": 2.457, + "args": { + "External id": 230753,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[65536, 1024], [], []], "Ev Idx": 864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115535423.732, "dur": 0.540, + "args": { + "External id": 230754,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115535425.463, "dur": 36.957, + "args": { + "External id": 230755,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024]], "Ev Idx": 866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115535463.542, "dur": 3.878, + "args": { + "External id": 230756,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115535464.006, "dur": 2.714, + "args": { + "External id": 230757,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115535465.391, "dur": 1.200, + "args": { + "External id": 230758,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115535469.831, "dur": 5.697, + "args": { + "External id": 230759,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115535471.005, "dur": 4.048, + "args": { + "External id": 230760,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115535472.442, "dur": 2.538, + "args": { + "External id": 230761,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115535476.017, "dur": 44.725, + "args": { + "External id": 230762,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535534.764, "dur": 35.731, + "args": { + "External id": 230763,"Record function id": 0, "Sequence number": 2757861, "Fwd thread id": 1, "Ev Idx": 874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535536.001, "dur": 4.933, + "args": { + "External id": 230764,"Sequence number": 2757861, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 875 + } + }, + { + "ph": "f", "id": 95, "pid": 4183440, "tid": 31337, "ts": 667115535536.001, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115535537.925, "dur": 2.872, + "args": { + "External id": 230765,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115535539.137, "dur": 1.533, + "args": { + "External id": 230766,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 4183440, "tid": 31337, + "ts": 667115535544.108, "dur": 22.354, + "args": { + "External id": 230767,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535574.207, "dur": 9.036, + "args": { + "External id": 230768,"Record function id": 0, "Sequence number": 2757860, "Fwd thread id": 1, "Ev Idx": 879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535575.182, "dur": 5.874, + "args": { + "External id": 230769,"Sequence number": 2757860, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 880 + } + }, + { + "ph": "f", "id": 96, "pid": 4183440, "tid": 31337, "ts": 667115535575.182, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115535575.979, "dur": 4.883, + "args": { + "External id": 230770,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115535577.304, "dur": 2.956, + "args": { + "External id": 230771,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115535579.108, "dur": 1.009, + "args": { + "External id": 230772,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115535587.649, "dur": 8.200, + "args": { + "External id": 230773,"Record function id": 0, "Ev Idx": 884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115535589.268, "dur": 6.019, + "args": { + "External id": 230774,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115535590.423, "dur": 4.444, + "args": { + "External id": 230775,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115535593.099, "dur": 1.651, + "args": { + "External id": 230776,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535599.281, "dur": 6.162, + "args": { + "External id": 230777,"Record function id": 0, "Sequence number": 2757859, "Fwd thread id": 1, "Ev Idx": 888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535600.753, "dur": 3.266, + "args": { + "External id": 230778,"Sequence number": 2757859, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 889 + } + }, + { + "ph": "f", "id": 97, "pid": 4183440, "tid": 31337, "ts": 667115535600.753, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115535601.761, "dur": 2.114, + "args": { + "External id": 230779,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115535602.793, "dur": 0.954, + "args": { + "External id": 230780,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535610.637, "dur": 137.031, + "args": { + "External id": 230781,"Record function id": 0, "Sequence number": 2757858, "Fwd thread id": 1, "Ev Idx": 892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535611.581, "dur": 127.243, + "args": { + "External id": 230782,"Sequence number": 2757858, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 893 + } + }, + { + "ph": "f", "id": 98, "pid": 4183440, "tid": 31337, "ts": 667115535611.581, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115535613.958, "dur": 4.879, + "args": { + "External id": 230783,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115535614.601, "dur": 3.715, + "args": { + "External id": 230784,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[65536, 1024], [], []], "Ev Idx": 895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115535617.776, "dur": 0.404, + "args": { + "External id": 230785,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115535619.496, "dur": 65.041, + "args": { + "External id": 230786,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024]], "Ev Idx": 897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115535687.014, "dur": 5.496, + "args": { + "External id": 230787,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115535687.879, "dur": 3.809, + "args": { + "External id": 230788,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115535690.550, "dur": 1.031, + "args": { + "External id": 230789,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115535693.846, "dur": 7.643, + "args": { + "External id": 230790,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115535698.826, "dur": 2.166, + "args": { + "External id": 230791,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115535700.506, "dur": 0.420, + "args": { + "External id": 230792,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115535702.062, "dur": 35.979, + "args": { + "External id": 230793,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535754.091, "dur": 27.561, + "args": { + "External id": 230794,"Record function id": 0, "Sequence number": 2757857, "Fwd thread id": 1, "Ev Idx": 905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535755.120, "dur": 4.341, + "args": { + "External id": 230795,"Sequence number": 2757857, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 906 + } + }, + { + "ph": "f", "id": 99, "pid": 4183440, "tid": 31337, "ts": 667115535755.120, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115535756.841, "dur": 2.457, + "args": { + "External id": 230796,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115535758.013, "dur": 1.158, + "args": { + "External id": 230797,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 31337, + "ts": 667115535762.139, "dur": 17.518, + "args": { + "External id": 230798,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535785.383, "dur": 9.375, + "args": { + "External id": 230799,"Record function id": 0, "Sequence number": 2757856, "Fwd thread id": 1, "Ev Idx": 910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115535788.278, "dur": 5.005, + "args": { + "External id": 230800,"Sequence number": 2757856, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 911 + } + }, + { + "ph": "f", "id": 100, "pid": 4183440, "tid": 31337, "ts": 667115535788.278, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115535789.236, "dur": 3.840, + "args": { + "External id": 230801,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115535790.245, "dur": 2.264, + "args": { + "External id": 230802,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115535791.736, "dur": 0.651, + "args": { + "External id": 230803,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115535799.089, "dur": 6.165, + "args": { + "External id": 230804,"Record function id": 0, "Ev Idx": 915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115535801.042, "dur": 3.695, + "args": { + "External id": 230805,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115535802.146, "dur": 2.245, + "args": { + "External id": 230806,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115535802.906, "dur": 1.378, + "args": { + "External id": 230807,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115535809.307, "dur": 357.646, + "args": { + "External id": 230808,"Record function id": 0, "Sequence number": 2757855, "Fwd thread id": 1, "Ev Idx": 919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115535810.773, "dur": 321.085, + "args": { + "External id": 230809,"Sequence number": 2757855, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 920 + } + }, + { + "ph": "f", "id": 101, "pid": 4183440, "tid": 31337, "ts": 667115535810.773, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115535845.569, "dur": 3.980, + "args": { + "External id": 230810,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115535848.082, "dur": 1.281, + "args": { + "External id": 230811,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115535863.935, "dur": 5.667, + "args": { + "External id": 230812,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115535879.048, "dur": 2.935, + "args": { + "External id": 230813,"Record function id": 0, "Concrete Inputs": ["[132, 1024]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115536026.465, "dur": 1.874, + "args": { + "External id": 230814,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 1024]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[132, 1024], []], "Ev Idx": 925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 31337, + "ts": 667115536032.366, "dur": 35.080, + "args": { + "External id": 230815,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[135168, 1024, 1], [], [], []], "Input Dims": [[1, 132, 1024], [], [], []], "Ev Idx": 926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115536042.313, "dur": 0.755, + "args": { + "External id": 230816,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 1024]", "[1024, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1, 1024], [], [], []], "Ev Idx": 927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115536075.999, "dur": 33.176, + "args": { + "External id": 230817,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[1, 1024], [], [], [], [], []], "Ev Idx": 928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115536077.759, "dur": 31.148, + "args": { + "External id": 230818,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], [], []], "Input Dims": [[1, 1024], [], [], [], [], [], []], "Ev Idx": 929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115536084.002, "dur": 5.541, + "args": { + "External id": 230819,"Record function id": 0, "Concrete Inputs": ["[1, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115536091.189, "dur": 17.174, + "args": { + "External id": 230820,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[1, 1024], [1, 1024], []], "Ev Idx": 931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 31337, + "ts": 667115536113.874, "dur": 2.653, + "args": { + "External id": 230821,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1]], "Input Dims": [[1, 1024], [1024]], "Ev Idx": 932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115536115.323, "dur": 1.106, + "args": { + "External id": 230822,"Record function id": 0, "Concrete Inputs": ["", "[1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[1, 1024], []], "Ev Idx": 933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115536122.643, "dur": 2.333, + "args": { + "External id": 230823,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115536124.027, "dur": 0.816, + "args": { + "External id": 230824,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 31337, + "ts": 667115536142.701, "dur": 20.020, + "args": { + "External id": 230825,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115536177.174, "dur": 8.516, + "args": { + "External id": 230826,"Record function id": 0, "Ev Idx": 937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115536179.328, "dur": 5.695, + "args": { + "External id": 230827,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115536181.755, "dur": 2.380, + "args": { + "External id": 230828,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115536182.642, "dur": 1.398, + "args": { + "External id": 230829,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115536189.576, "dur": 4.697, + "args": { + "External id": 230830,"Record function id": 0, "Sequence number": 2757854, "Fwd thread id": 1, "Ev Idx": 941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115536190.482, "dur": 0.893, + "args": { + "External id": 230831,"Sequence number": 2757854, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 942 + } + }, + { + "ph": "f", "id": 102, "pid": 4183440, "tid": 31337, "ts": 667115536190.482, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115536198.223, "dur": 416.264, + "args": { + "External id": 230832,"Record function id": 0, "Sequence number": 2757853, "Fwd thread id": 1, "Ev Idx": 943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115536199.659, "dur": 402.546, + "args": { + "External id": 230833,"Sequence number": 2757853, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 944 + } + }, + { + "ph": "f", "id": 103, "pid": 4183440, "tid": 31337, "ts": 667115536199.659, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115536229.811, "dur": 8.073, + "args": { + "External id": 230834,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 4183440, "tid": 31337, + "ts": 667115536234.567, "dur": 2.983, + "args": { + "External id": 230835,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]", "[4096, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[16777216, 4096, 1], [], []], "Input Dims": [[16, 4096, 1024], [], []], "Ev Idx": 946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115536240.791, "dur": 5.120, + "args": { + "External id": 230836,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115536242.311, "dur": 2.938, + "args": { + "External id": 230837,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2816, 1], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115536244.272, "dur": 0.789, + "args": { + "External id": 230838,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 31337, + "ts": 667115536249.741, "dur": 84.883, + "args": { + "External id": 230839,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [1, 2816], []], "Input Dims": [[65536, 1024], [2816, 1024], []], "Ev Idx": 950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115536250.669, "dur": 7.033, + "args": { + "External id": 230840,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2816]], "Input Dims": [[2816, 1024]], "Ev Idx": 951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115536253.555, "dur": 3.663, + "args": { + "External id": 230841,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2816], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115536255.070, "dur": 2.031, + "args": { + "External id": 230842,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[2816, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2816], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 31337, + "ts": 667115536258.782, "dur": 75.430, + "args": { + "External id": 230843,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816]], "Ev Idx": 954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115536260.157, "dur": 73.036, + "args": { + "External id": 230844,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816]], "Ev Idx": 955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 31337, + "ts": 667115536338.173, "dur": 3.022, + "args": { + "External id": 230845,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [11534336, 2816, 1]], "Input Dims": [[65536, 2816], [16, 4096, 2816]], "Ev Idx": 956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115536339.644, "dur": 1.408, + "args": { + "External id": 230846,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1], []], "Input Dims": [[65536, 2816], []], "Ev Idx": 957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115536372.625, "dur": 4.298, + "args": { + "External id": 230847,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2816]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115536378.391, "dur": 1.860, + "args": { + "External id": 230848,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2816]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115536381.426, "dur": 1.619, + "args": { + "External id": 230849,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2816]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115536414.176, "dur": 2.365, + "args": { + "External id": 230850,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115536414.982, "dur": 1.409, + "args": { + "External id": 230851,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 4183440, "tid": 31337, + "ts": 667115536438.627, "dur": 142.408, + "args": { + "External id": 230852,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[4096, 1], [2816, 1]], []], "Input Dims": [[], [[65536, 1024], [65536, 2816]], []], "Ev Idx": 963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 31337, + "ts": 667115536443.721, "dur": 5.740, + "args": { + "External id": 230853,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115536447.397, "dur": 0.943, + "args": { + "External id": 230854,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024, 1]", "[4096, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115536451.180, "dur": 8.103, + "args": { + "External id": 230855,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1, 1], []], "Input Dims": [[65536, 1024, 1], []], "Ev Idx": 966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115536456.528, "dur": 2.025, + "args": { + "External id": 230856,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1, 65536]", "[1, 1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1, 1], [], [], []], "Input Dims": [[65536, 1024, 1], [], [], []], "Ev Idx": 967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 31337, + "ts": 667115536460.478, "dur": 2.446, + "args": { + "External id": 230857,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], []], "Input Dims": [[65536, 2816], []], "Ev Idx": 968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115536462.154, "dur": 0.402, + "args": { + "External id": 230858,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816, 1]", "[2816, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[65536, 2816], [], [], []], "Ev Idx": 969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115536463.926, "dur": 3.001, + "args": { + "External id": 230859,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1, 1], []], "Input Dims": [[65536, 2816, 1], []], "Ev Idx": 970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115536465.854, "dur": 0.553, + "args": { + "External id": 230860,"Record function id": 0, "Concrete Inputs": ["", "[1, 2816, 65536]", "[1, 1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1, 1], [], [], []], "Input Dims": [[65536, 2816, 1], [], [], []], "Ev Idx": 971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115536470.502, "dur": 3.001, + "args": { + "External id": 230861,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 4096], []], "Input Dims": [[1024, 1, 65536], []], "Ev Idx": 972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115536472.532, "dur": 0.636, + "args": { + "External id": 230862,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536, 1]", "[1, 4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 4096], [], [], []], "Input Dims": [[1024, 1, 65536], [], [], []], "Ev Idx": 973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115536474.707, "dur": 5.631, + "args": { + "External id": 230863,"Record function id": 0, "Concrete Inputs": ["", "[1, 1024, 65536]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 4096, 1], []], "Input Dims": [[1024, 65536, 1], []], "Ev Idx": 974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 4183440, "tid": 31337, + "ts": 667115536478.519, "dur": 1.633, + "args": { + "External id": 230864,"Record function id": 0, "Concrete Inputs": ["", "[1, 1024, 65536]", "[1024, 1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 4096, 1], [], []], "Input Dims": [[1024, 65536, 1], [], []], "Ev Idx": 975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115536481.466, "dur": 2.805, + "args": { + "External id": 230865,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 2816], []], "Input Dims": [[1, 2816, 65536], []], "Ev Idx": 976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115536483.654, "dur": 0.321, + "args": { + "External id": 230866,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816, 1]", "[2816, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 2816], [], [], []], "Input Dims": [[1, 2816, 65536], [], [], []], "Ev Idx": 977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115536487.468, "dur": 24.573, + "args": { + "External id": 230867,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1, 1], []], "Input Dims": [[65536, 2816, 1], []], "Ev Idx": 978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115536488.963, "dur": 22.637, + "args": { + "External id": 230868,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1, 1], []], "Input Dims": [[65536, 2816, 1], []], "Ev Idx": 979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115536514.242, "dur": 52.563, + "args": { + "External id": 230869,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1, 4096], [184549376, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816]], "Ev Idx": 980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115536569.089, "dur": 2.908, + "args": { + "External id": 230870,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2883584, 2816, 1], []], "Input Dims": [[1, 1024, 2816], []], "Ev Idx": 981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115536573.021, "dur": 3.449, + "args": { + "External id": 230871,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 2816, 1], []], "Input Dims": [[1024, 1, 2816], []], "Ev Idx": 982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115536575.174, "dur": 0.788, + "args": { + "External id": 230872,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816, 1]", "[2816, 1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 2816, 1], [], [], []], "Input Dims": [[1024, 1, 2816], [], [], []], "Ev Idx": 983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115536578.909, "dur": 1.009, + "args": { + "External id": 230873,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1, 2816], []], "Input Dims": [[1024, 2816, 1], []], "Ev Idx": 984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115536626.408, "dur": 9.683, + "args": { + "External id": 230874,"Record function id": 0, "Ev Idx": 985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115536628.966, "dur": 6.377, + "args": { + "External id": 230875,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115536631.373, "dur": 3.114, + "args": { + "External id": 230876,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115536632.447, "dur": 1.953, + "args": { + "External id": 230877,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115536639.899, "dur": 7.105, + "args": { + "External id": 230878,"Record function id": 0, "Sequence number": 2757852, "Fwd thread id": 1, "Ev Idx": 989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115536641.294, "dur": 3.671, + "args": { + "External id": 230879,"Sequence number": 2757852, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[11534336, 2816, 1]], "Input Dims": [[16, 4096, 2816]], "Ev Idx": 990 + } + }, + { + "ph": "f", "id": 104, "pid": 4183440, "tid": 31337, "ts": 667115536641.294, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115536642.891, "dur": 1.853, + "args": { + "External id": 230880,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115536643.690, "dur": 0.912, + "args": { + "External id": 230881,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115536650.612, "dur": 157.468, + "args": { + "External id": 230882,"Record function id": 0, "Sequence number": 2757851, "Fwd thread id": 1, "Ev Idx": 993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115536651.479, "dur": 149.188, + "args": { + "External id": 230883,"Sequence number": 2757851, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[65536, 2816]], "Ev Idx": 994 + } + }, + { + "ph": "f", "id": 105, "pid": 4183440, "tid": 31337, "ts": 667115536651.479, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115536690.626, "dur": 7.630, + "args": { + "External id": 230884,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[65536, 2816]], "Ev Idx": 995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115536692.235, "dur": 5.152, + "args": { + "External id": 230885,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2816, 1], [], []], "Input Dims": [[65536, 2816], [], []], "Ev Idx": 996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115536696.083, "dur": 0.971, + "args": { + "External id": 230886,"Record function id": 0, "Concrete Inputs": ["", "[2816, 65536]", "[1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[65536, 2816], [], [], []], "Ev Idx": 997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115536699.399, "dur": 46.384, + "args": { + "External id": 230887,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024]], "Ev Idx": 998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115536747.016, "dur": 4.382, + "args": { + "External id": 230888,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115536747.521, "dur": 3.133, + "args": { + "External id": 230889,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 1000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115536749.269, "dur": 1.213, + "args": { + "External id": 230890,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 1001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115536752.669, "dur": 5.114, + "args": { + "External id": 230891,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 1002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115536755.680, "dur": 1.642, + "args": { + "External id": 230892,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 1003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115536756.834, "dur": 0.363, + "args": { + "External id": 230893,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 1004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115536758.359, "dur": 41.326, + "args": { + "External id": 230894,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024]], "Ev Idx": 1005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115536814.380, "dur": 7.016, + "args": { + "External id": 230895,"Record function id": 0, "Sequence number": 2757850, "Fwd thread id": 1, "Ev Idx": 1006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115536815.421, "dur": 4.702, + "args": { + "External id": 230896,"Sequence number": 2757850, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1007 + } + }, + { + "ph": "f", "id": 106, "pid": 4183440, "tid": 31337, "ts": 667115536815.421, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115536817.078, "dur": 2.899, + "args": { + "External id": 230897,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115536818.527, "dur": 1.312, + "args": { + "External id": 230898,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115536825.027, "dur": 8.556, + "args": { + "External id": 230899,"Record function id": 0, "Sequence number": 2757849, "Fwd thread id": 1, "Ev Idx": 1010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115536825.831, "dur": 5.370, + "args": { + "External id": 230900,"Sequence number": 2757849, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 1011 + } + }, + { + "ph": "f", "id": 107, "pid": 4183440, "tid": 31337, "ts": 667115536825.831, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115536826.544, "dur": 4.456, + "args": { + "External id": 230901,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 1012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115536828.394, "dur": 2.096, + "args": { + "External id": 230902,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 1013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115536829.855, "dur": 0.540, + "args": { + "External id": 230903,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 1014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115536837.750, "dur": 6.444, + "args": { + "External id": 230904,"Record function id": 0, "Ev Idx": 1015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115536839.518, "dur": 4.115, + "args": { + "External id": 230905,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115536840.912, "dur": 2.370, + "args": { + "External id": 230906,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115536841.809, "dur": 1.367, + "args": { + "External id": 230907,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115536849.294, "dur": 5.662, + "args": { + "External id": 230908,"Record function id": 0, "Sequence number": 2757848, "Fwd thread id": 1, "Ev Idx": 1019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115536850.431, "dur": 2.625, + "args": { + "External id": 230909,"Sequence number": 2757848, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[11534336, 2816, 1]], "Input Dims": [[16, 4096, 2816]], "Ev Idx": 1020 + } + }, + { + "ph": "f", "id": 108, "pid": 4183440, "tid": 31337, "ts": 667115536850.431, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115536851.323, "dur": 1.586, + "args": { + "External id": 230910,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 1021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115536851.980, "dur": 0.783, + "args": { + "External id": 230911,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 1022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115536859.814, "dur": 109.970, + "args": { + "External id": 230912,"Record function id": 0, "Sequence number": 2757847, "Fwd thread id": 1, "Ev Idx": 1023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115536881.667, "dur": 81.069, + "args": { + "External id": 230913,"Sequence number": 2757847, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[65536, 2816]], "Ev Idx": 1024 + } + }, + { + "ph": "f", "id": 109, "pid": 4183440, "tid": 31337, "ts": 667115536881.667, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115536883.480, "dur": 3.289, + "args": { + "External id": 230914,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[65536, 2816]], "Ev Idx": 1025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115536883.960, "dur": 2.266, + "args": { + "External id": 230915,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2816, 1], [], []], "Input Dims": [[65536, 2816], [], []], "Ev Idx": 1026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115536885.647, "dur": 0.437, + "args": { + "External id": 230916,"Record function id": 0, "Concrete Inputs": ["", "[2816, 65536]", "[1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[65536, 2816], [], [], []], "Ev Idx": 1027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115536887.247, "dur": 28.180, + "args": { + "External id": 230917,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024]], "Ev Idx": 1028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115536917.975, "dur": 4.372, + "args": { + "External id": 230918,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115536918.444, "dur": 3.331, + "args": { + "External id": 230919,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 1030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115536920.005, "dur": 1.603, + "args": { + "External id": 230920,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 1031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115536923.415, "dur": 4.801, + "args": { + "External id": 230921,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 1032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115536924.368, "dur": 3.405, + "args": { + "External id": 230922,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 1033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115536925.556, "dur": 2.092, + "args": { + "External id": 230923,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 1034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115536930.139, "dur": 31.934, + "args": { + "External id": 230924,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024]], "Ev Idx": 1035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115536974.284, "dur": 30.232, + "args": { + "External id": 230925,"Record function id": 0, "Sequence number": 2757846, "Fwd thread id": 1, "Ev Idx": 1036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115536975.317, "dur": 3.779, + "args": { + "External id": 230926,"Sequence number": 2757846, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1037 + } + }, + { + "ph": "f", "id": 110, "pid": 4183440, "tid": 31337, "ts": 667115536975.317, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115536976.946, "dur": 1.997, + "args": { + "External id": 230927,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115536977.897, "dur": 0.893, + "args": { + "External id": 230928,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 4183440, "tid": 31337, + "ts": 667115536982.283, "dur": 19.339, + "args": { + "External id": 230929,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 1040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115537007.997, "dur": 8.989, + "args": { + "External id": 230930,"Record function id": 0, "Sequence number": 2757845, "Fwd thread id": 1, "Ev Idx": 1041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115537008.966, "dur": 5.704, + "args": { + "External id": 230931,"Sequence number": 2757845, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 1042 + } + }, + { + "ph": "f", "id": 111, "pid": 4183440, "tid": 31337, "ts": 667115537008.966, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115537009.555, "dur": 4.893, + "args": { + "External id": 230932,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 1043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115537010.150, "dur": 3.788, + "args": { + "External id": 230933,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 1044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115537013.355, "dur": 0.471, + "args": { + "External id": 230934,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 1045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115537020.940, "dur": 5.089, + "args": { + "External id": 230935,"Record function id": 0, "Ev Idx": 1046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115537022.595, "dur": 2.850, + "args": { + "External id": 230936,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115537023.585, "dur": 1.576, + "args": { + "External id": 230937,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115537024.028, "dur": 1.033, + "args": { + "External id": 230938,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115537030.191, "dur": 383.369, + "args": { + "External id": 230939,"Record function id": 0, "Sequence number": 2757844, "Fwd thread id": 1, "Ev Idx": 1050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115537031.794, "dur": 350.303, + "args": { + "External id": 230940,"Sequence number": 2757844, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [16777216, 4096, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 1051 + } + }, + { + "ph": "f", "id": 112, "pid": 4183440, "tid": 31337, "ts": 667115537031.794, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183440, "tid": 31337, + "ts": 667115537055.641, "dur": 32.202, + "args": { + "External id": 230941,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 31337, + "ts": 667115537056.860, "dur": 30.786, + "args": { + "External id": 230942,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115537059.853, "dur": 5.634, + "args": { + "External id": 230943,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], [], [], []], "Ev Idx": 1054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115537062.305, "dur": 2.762, + "args": { + "External id": 230944,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 1024]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115537066.699, "dur": 20.389, + "args": { + "External id": 230945,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 1056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115537098.855, "dur": 2.083, + "args": { + "External id": 230946,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115537099.739, "dur": 1.091, + "args": { + "External id": 230947,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115537106.117, "dur": 2.715, + "args": { + "External id": 230948,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115537106.918, "dur": 1.820, + "args": { + "External id": 230949,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115537119.698, "dur": 1.952, + "args": { + "External id": 230950,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115537132.764, "dur": 3.039, + "args": { + "External id": 230951,"Record function id": 0, "Concrete Inputs": ["[132, 1024]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115537284.920, "dur": 2.293, + "args": { + "External id": 230952,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 1024]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[132, 1024], []], "Ev Idx": 1063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 31337, + "ts": 667115537291.293, "dur": 28.018, + "args": { + "External id": 230953,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[135168, 1024, 1], [], [], []], "Input Dims": [[1, 132, 1024], [], [], []], "Ev Idx": 1064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115537299.520, "dur": 0.657, + "args": { + "External id": 230954,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 1024]", "[1024, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1, 1024], [], [], []], "Ev Idx": 1065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115537324.447, "dur": 25.946, + "args": { + "External id": 230955,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[1, 1024], [], [], [], [], []], "Ev Idx": 1066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115537326.120, "dur": 24.065, + "args": { + "External id": 230956,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], [], []], "Input Dims": [[1, 1024], [], [], [], [], [], []], "Ev Idx": 1067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115537330.302, "dur": 4.158, + "args": { + "External id": 230957,"Record function id": 0, "Concrete Inputs": ["[1, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115537335.897, "dur": 13.749, + "args": { + "External id": 230958,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[1, 1024], [1, 1024], []], "Ev Idx": 1069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 31337, + "ts": 667115537354.327, "dur": 2.526, + "args": { + "External id": 230959,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1]], "Input Dims": [[1, 1024], [1024]], "Ev Idx": 1070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115537355.591, "dur": 1.128, + "args": { + "External id": 230960,"Record function id": 0, "Concrete Inputs": ["", "[1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[1, 1024], []], "Ev Idx": 1071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115537364.744, "dur": 2.696, + "args": { + "External id": 230961,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115537366.077, "dur": 1.201, + "args": { + "External id": 230962,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115537370.117, "dur": 3.661, + "args": { + "External id": 230963,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115537371.297, "dur": 2.387, + "args": { + "External id": 230964,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 31337, + "ts": 667115537395.159, "dur": 16.808, + "args": { + "External id": 230965,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 1076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115537423.290, "dur": 9.131, + "args": { + "External id": 230966,"Record function id": 0, "Ev Idx": 1077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115537425.572, "dur": 6.186, + "args": { + "External id": 230967,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115537427.232, "dur": 3.716, + "args": { + "External id": 230968,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115537429.408, "dur": 1.420, + "args": { + "External id": 230969,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115537436.189, "dur": 8.070, + "args": { + "External id": 230970,"Record function id": 0, "Sequence number": 2757843, "Fwd thread id": 1, "Ev Idx": 1081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115537437.544, "dur": 4.371, + "args": { + "External id": 230971,"Sequence number": 2757843, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1082 + } + }, + { + "ph": "f", "id": 113, "pid": 4183440, "tid": 31337, "ts": 667115537437.544, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115537439.582, "dur": 2.179, + "args": { + "External id": 230972,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115537440.428, "dur": 1.207, + "args": { + "External id": 230973,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115537447.648, "dur": 158.925, + "args": { + "External id": 230974,"Record function id": 0, "Sequence number": 2757842, "Fwd thread id": 1, "Ev Idx": 1085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115537448.288, "dur": 150.629, + "args": { + "External id": 230975,"Sequence number": 2757842, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1086 + } + }, + { + "ph": "f", "id": 114, "pid": 4183440, "tid": 31337, "ts": 667115537448.288, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115537451.210, "dur": 6.466, + "args": { + "External id": 230976,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115537452.348, "dur": 4.740, + "args": { + "External id": 230977,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[65536, 1024], [], []], "Ev Idx": 1088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115537455.956, "dur": 0.952, + "args": { + "External id": 230978,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 1089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115537458.850, "dur": 78.993, + "args": { + "External id": 230979,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024]], "Ev Idx": 1090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115537540.416, "dur": 6.980, + "args": { + "External id": 230980,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115537541.537, "dur": 4.902, + "args": { + "External id": 230981,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115537543.847, "dur": 2.410, + "args": { + "External id": 230982,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115537549.025, "dur": 5.388, + "args": { + "External id": 230983,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115537552.183, "dur": 1.739, + "args": { + "External id": 230984,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115537553.477, "dur": 0.301, + "args": { + "External id": 230985,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115537554.994, "dur": 42.910, + "args": { + "External id": 230986,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 1097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115537612.929, "dur": 9.081, + "args": { + "External id": 230987,"Record function id": 0, "Sequence number": 2757841, "Fwd thread id": 1, "Ev Idx": 1098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115537613.993, "dur": 6.410, + "args": { + "External id": 230988,"Sequence number": 2757841, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1099 + } + }, + { + "ph": "f", "id": 115, "pid": 4183440, "tid": 31337, "ts": 667115537613.993, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115537616.047, "dur": 4.194, + "args": { + "External id": 230989,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115537617.027, "dur": 3.059, + "args": { + "External id": 230990,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115537626.154, "dur": 9.200, + "args": { + "External id": 230991,"Record function id": 0, "Sequence number": 2757840, "Fwd thread id": 1, "Ev Idx": 1102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115537627.042, "dur": 6.408, + "args": { + "External id": 230992,"Sequence number": 2757840, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1103 + } + }, + { + "ph": "f", "id": 116, "pid": 4183440, "tid": 31337, "ts": 667115537627.042, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115537627.872, "dur": 5.380, + "args": { + "External id": 230993,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115537630.515, "dur": 2.260, + "args": { + "External id": 230994,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115537632.233, "dur": 0.421, + "args": { + "External id": 230995,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115537639.644, "dur": 5.786, + "args": { + "External id": 230996,"Record function id": 0, "Ev Idx": 1107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115537641.144, "dur": 3.742, + "args": { + "External id": 230997,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115537642.491, "dur": 2.090, + "args": { + "External id": 230998,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115537643.173, "dur": 1.289, + "args": { + "External id": 230999,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115537650.502, "dur": 42.777, + "args": { + "External id": 231000,"Record function id": 0, "Sequence number": 2757839, "Fwd thread id": 1, "Ev Idx": 1111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115537651.556, "dur": 38.908, + "args": { + "External id": 231001,"Sequence number": 2757839, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1112 + } + }, + { + "ph": "f", "id": 117, "pid": 4183440, "tid": 31337, "ts": 667115537651.556, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115537652.797, "dur": 37.477, + "args": { + "External id": 231002,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115537687.908, "dur": 2.062, + "args": { + "External id": 231003,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 4183440, "tid": 31337, + "ts": 667115537699.410, "dur": 289.760, + "args": { + "External id": 231004,"Record function id": 0, "Sequence number": 2757838, "Fwd thread id": 1, "Ev Idx": 1115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 4183440, "tid": 31337, + "ts": 667115537701.162, "dur": 272.902, + "args": { + "External id": 231005,"Sequence number": 2757838, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 1116 + } + }, + { + "ph": "f", "id": 118, "pid": 4183440, "tid": 31337, "ts": 667115537701.162, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115537717.436, "dur": 8.643, + "args": { + "External id": 231006,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 1117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115537720.926, "dur": 4.740, + "args": { + "External id": 231007,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115537728.429, "dur": 4.966, + "args": { + "External id": 231008,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 1119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115537730.122, "dur": 3.055, + "args": { + "External id": 231009,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115537743.610, "dur": 5.027, + "args": { + "External id": 231010,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 1121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115537746.804, "dur": 1.648, + "args": { + "External id": 231011,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115537775.889, "dur": 173.621, + "args": { + "External id": 231012,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115537852.773, "dur": 4.846, + "args": { + "External id": 231013,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115537859.296, "dur": 4.232, + "args": { + "External id": 231014,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 4183440, "tid": 31337, + "ts": 667115537961.990, "dur": 3.460, + "args": { + "External id": 231015,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 1126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 4183440, "tid": 31337, + "ts": 667115537968.187, "dur": 0.864, + "args": { + "External id": 231016,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 1127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 4183440, "tid": 31337, + "ts": 667115537970.852, "dur": 0.746, + "args": { + "External id": 231017,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 1128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115537996.723, "dur": 217.742, + "args": { + "External id": 231018,"Record function id": 0, "Sequence number": 2757837, "Fwd thread id": 1, "Ev Idx": 1129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115537998.779, "dur": 208.661, + "args": { + "External id": 231019,"Sequence number": 2757837, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 1130 + } + }, + { + "ph": "f", "id": 119, "pid": 4183440, "tid": 31337, "ts": 667115537998.779, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 31337, + "ts": 667115538017.339, "dur": 42.084, + "args": { + "External id": 231020,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 1131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115538020.459, "dur": 2.608, + "args": { + "External id": 231021,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115538024.460, "dur": 34.493, + "args": { + "External id": 231022,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], []], "Ev Idx": 1133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115538068.928, "dur": 5.868, + "args": { + "External id": 231023,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 1134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115538070.668, "dur": 3.839, + "args": { + "External id": 231024,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115538221.792, "dur": 144.629, + "args": { + "External id": 231025,"Record function id": 0, "Sequence number": 2757836, "Fwd thread id": 1, "Ev Idx": 1136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115538223.823, "dur": 136.374, + "args": { + "External id": 231026,"Sequence number": 2757836, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 1137 + } + }, + { + "ph": "f", "id": 120, "pid": 4183440, "tid": 31337, "ts": 667115538223.823, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 31337, + "ts": 667115538235.360, "dur": 34.100, + "args": { + "External id": 231027,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 1138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115538237.658, "dur": 2.720, + "args": { + "External id": 231028,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115538245.218, "dur": 23.709, + "args": { + "External id": 231029,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], []], "Ev Idx": 1140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115538276.558, "dur": 4.241, + "args": { + "External id": 231030,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 1141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115538278.369, "dur": 2.107, + "args": { + "External id": 231031,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538372.469, "dur": 15.834, + "args": { + "External id": 231032,"Record function id": 0, "Sequence number": 2757835, "Fwd thread id": 1, "Ev Idx": 1143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538373.948, "dur": 11.463, + "args": { + "External id": 231033,"Sequence number": 2757835, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 1144 + } + }, + { + "ph": "f", "id": 121, "pid": 4183440, "tid": 31337, "ts": 667115538373.948, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115538376.728, "dur": 8.437, + "args": { + "External id": 231034,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 1145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115538378.589, "dur": 6.338, + "args": { + "External id": 231035,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 1146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538391.794, "dur": 8.300, + "args": { + "External id": 231036,"Record function id": 0, "Sequence number": 2757834, "Fwd thread id": 1, "Ev Idx": 1147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538394.305, "dur": 3.807, + "args": { + "External id": 231037,"Sequence number": 2757834, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 1148 + } + }, + { + "ph": "f", "id": 122, "pid": 4183440, "tid": 31337, "ts": 667115538394.305, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115538396.075, "dur": 1.893, + "args": { + "External id": 231038,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 1149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115538396.875, "dur": 0.961, + "args": { + "External id": 231039,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 1150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538403.269, "dur": 6.283, + "args": { + "External id": 231040,"Record function id": 0, "Sequence number": 2757833, "Fwd thread id": 1, "Ev Idx": 1151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538404.213, "dur": 3.306, + "args": { + "External id": 231041,"Sequence number": 2757833, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 1152 + } + }, + { + "ph": "f", "id": 123, "pid": 4183440, "tid": 31337, "ts": 667115538404.213, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115538405.464, "dur": 1.913, + "args": { + "External id": 231042,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 1153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115538406.415, "dur": 0.856, + "args": { + "External id": 231043,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 1154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538413.397, "dur": 9.068, + "args": { + "External id": 231044,"Record function id": 0, "Sequence number": 2757832, "Fwd thread id": 1, "Ev Idx": 1155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538414.557, "dur": 5.934, + "args": { + "External id": 231045,"Sequence number": 2757832, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1156 + } + }, + { + "ph": "f", "id": 124, "pid": 4183440, "tid": 31337, "ts": 667115538414.557, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115538415.922, "dur": 4.425, + "args": { + "External id": 231046,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115538418.945, "dur": 1.268, + "args": { + "External id": 231047,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538426.157, "dur": 184.594, + "args": { + "External id": 231048,"Record function id": 0, "Sequence number": 2757831, "Fwd thread id": 1, "Ev Idx": 1159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538426.993, "dur": 174.986, + "args": { + "External id": 231049,"Sequence number": 2757831, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1160 + } + }, + { + "ph": "f", "id": 125, "pid": 4183440, "tid": 31337, "ts": 667115538426.993, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115538430.135, "dur": 7.140, + "args": { + "External id": 231050,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115538431.939, "dur": 4.673, + "args": { + "External id": 231051,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[65536, 1024], [], []], "Ev Idx": 1162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115538434.530, "dur": 1.765, + "args": { + "External id": 231052,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 1163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115538438.693, "dur": 99.680, + "args": { + "External id": 231053,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024]], "Ev Idx": 1164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115538543.001, "dur": 6.337, + "args": { + "External id": 231054,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115538544.197, "dur": 4.048, + "args": { + "External id": 231055,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115538546.304, "dur": 1.751, + "args": { + "External id": 231056,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115538551.267, "dur": 3.723, + "args": { + "External id": 231057,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115538552.604, "dur": 1.904, + "args": { + "External id": 231058,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115538553.971, "dur": 0.406, + "args": { + "External id": 231059,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115538557.560, "dur": 43.676, + "args": { + "External id": 231060,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 1171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538619.387, "dur": 8.735, + "args": { + "External id": 231061,"Record function id": 0, "Sequence number": 2757830, "Fwd thread id": 1, "Ev Idx": 1172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538620.711, "dur": 5.481, + "args": { + "External id": 231062,"Sequence number": 2757830, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1173 + } + }, + { + "ph": "f", "id": 126, "pid": 4183440, "tid": 31337, "ts": 667115538620.711, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115538622.749, "dur": 3.305, + "args": { + "External id": 231063,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115538624.258, "dur": 1.656, + "args": { + "External id": 231064,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538631.687, "dur": 9.602, + "args": { + "External id": 231065,"Record function id": 0, "Sequence number": 2757829, "Fwd thread id": 1, "Ev Idx": 1176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538632.620, "dur": 6.629, + "args": { + "External id": 231066,"Sequence number": 2757829, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1177 + } + }, + { + "ph": "f", "id": 127, "pid": 4183440, "tid": 31337, "ts": 667115538632.620, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115538633.594, "dur": 5.453, + "args": { + "External id": 231067,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115538634.319, "dur": 4.194, + "args": { + "External id": 231068,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115538637.967, "dur": 0.436, + "args": { + "External id": 231069,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115538647.140, "dur": 45.648, + "args": { + "External id": 231070,"Record function id": 0, "Ev Idx": 1181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115538648.911, "dur": 42.361, + "args": { + "External id": 231071,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115538651.607, "dur": 39.096, + "args": { + "External id": 231072,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115538686.448, "dur": 3.852, + "args": { + "External id": 231073,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538698.270, "dur": 8.432, + "args": { + "External id": 231074,"Record function id": 0, "Sequence number": 2757828, "Fwd thread id": 1, "Ev Idx": 1185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538700.506, "dur": 4.271, + "args": { + "External id": 231075,"Sequence number": 2757828, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1186 + } + }, + { + "ph": "f", "id": 128, "pid": 4183440, "tid": 31337, "ts": 667115538700.506, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115538702.024, "dur": 2.553, + "args": { + "External id": 231076,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115538702.837, "dur": 1.600, + "args": { + "External id": 231077,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538710.120, "dur": 103.171, + "args": { + "External id": 231078,"Record function id": 0, "Sequence number": 2757827, "Fwd thread id": 1, "Ev Idx": 1189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538711.076, "dur": 96.195, + "args": { + "External id": 231079,"Sequence number": 2757827, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1190 + } + }, + { + "ph": "f", "id": 129, "pid": 4183440, "tid": 31337, "ts": 667115538711.076, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115538715.134, "dur": 3.646, + "args": { + "External id": 231080,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115538715.731, "dur": 2.565, + "args": { + "External id": 231081,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[65536, 1024], [], []], "Ev Idx": 1192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115538717.476, "dur": 0.680, + "args": { + "External id": 231082,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 1193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115538719.703, "dur": 40.959, + "args": { + "External id": 231083,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024]], "Ev Idx": 1194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115538761.655, "dur": 4.167, + "args": { + "External id": 231084,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115538762.462, "dur": 2.698, + "args": { + "External id": 231085,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115538764.327, "dur": 0.717, + "args": { + "External id": 231086,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115538768.722, "dur": 5.594, + "args": { + "External id": 231087,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115538770.000, "dur": 3.829, + "args": { + "External id": 231088,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115538771.667, "dur": 2.050, + "args": { + "External id": 231089,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115538774.988, "dur": 31.557, + "args": { + "External id": 231090,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 1201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538817.977, "dur": 35.075, + "args": { + "External id": 231091,"Record function id": 0, "Sequence number": 2757826, "Fwd thread id": 1, "Ev Idx": 1202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538818.934, "dur": 6.835, + "args": { + "External id": 231092,"Sequence number": 2757826, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1203 + } + }, + { + "ph": "f", "id": 130, "pid": 4183440, "tid": 31337, "ts": 667115538818.934, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115538820.787, "dur": 4.839, + "args": { + "External id": 231093,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115538824.071, "dur": 1.433, + "args": { + "External id": 231094,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 4183440, "tid": 31337, + "ts": 667115538829.268, "dur": 21.348, + "args": { + "External id": 231095,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 1206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538856.557, "dur": 8.028, + "args": { + "External id": 231096,"Record function id": 0, "Sequence number": 2757825, "Fwd thread id": 1, "Ev Idx": 1207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538857.410, "dur": 5.551, + "args": { + "External id": 231097,"Sequence number": 2757825, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1208 + } + }, + { + "ph": "f", "id": 131, "pid": 4183440, "tid": 31337, "ts": 667115538857.410, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115538858.539, "dur": 4.207, + "args": { + "External id": 231098,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115538859.223, "dur": 2.999, + "args": { + "External id": 231099,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115538861.442, "dur": 0.650, + "args": { + "External id": 231100,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115538868.895, "dur": 8.333, + "args": { + "External id": 231101,"Record function id": 0, "Ev Idx": 1212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115538870.965, "dur": 5.737, + "args": { + "External id": 231102,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115538872.299, "dur": 3.851, + "args": { + "External id": 231103,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115538874.772, "dur": 1.271, + "args": { + "External id": 231104,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538880.615, "dur": 8.607, + "args": { + "External id": 231105,"Record function id": 0, "Sequence number": 2757824, "Fwd thread id": 1, "Ev Idx": 1216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538882.055, "dur": 5.145, + "args": { + "External id": 231106,"Sequence number": 2757824, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1217 + } + }, + { + "ph": "f", "id": 132, "pid": 4183440, "tid": 31337, "ts": 667115538882.055, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115538883.189, "dur": 3.859, + "args": { + "External id": 231107,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115538885.757, "dur": 1.158, + "args": { + "External id": 231108,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538892.282, "dur": 94.243, + "args": { + "External id": 231109,"Record function id": 0, "Sequence number": 2757823, "Fwd thread id": 1, "Ev Idx": 1220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538893.366, "dur": 86.802, + "args": { + "External id": 231110,"Sequence number": 2757823, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1221 + } + }, + { + "ph": "f", "id": 133, "pid": 4183440, "tid": 31337, "ts": 667115538893.366, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115538897.038, "dur": 3.637, + "args": { + "External id": 231111,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115538897.772, "dur": 2.439, + "args": { + "External id": 231112,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[65536, 1024], [], []], "Ev Idx": 1223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115538899.499, "dur": 0.590, + "args": { + "External id": 231113,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 1224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115538901.445, "dur": 35.029, + "args": { + "External id": 231114,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024]], "Ev Idx": 1225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115538937.496, "dur": 6.767, + "args": { + "External id": 231115,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115538937.989, "dur": 5.579, + "args": { + "External id": 231116,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115538941.280, "dur": 2.081, + "args": { + "External id": 231117,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115538945.208, "dur": 3.324, + "args": { + "External id": 231118,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115538946.224, "dur": 1.863, + "args": { + "External id": 231119,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115538947.546, "dur": 0.473, + "args": { + "External id": 231120,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115538949.161, "dur": 30.370, + "args": { + "External id": 231121,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 1232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538990.924, "dur": 26.581, + "args": { + "External id": 231122,"Record function id": 0, "Sequence number": 2757822, "Fwd thread id": 1, "Ev Idx": 1233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115538992.110, "dur": 5.509, + "args": { + "External id": 231123,"Sequence number": 2757822, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1234 + } + }, + { + "ph": "f", "id": 134, "pid": 4183440, "tid": 31337, "ts": 667115538992.110, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115538993.499, "dur": 3.976, + "args": { + "External id": 231124,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115538996.243, "dur": 1.087, + "args": { + "External id": 231125,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 31337, + "ts": 667115539000.010, "dur": 15.502, + "args": { + "External id": 231126,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 1237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115539021.129, "dur": 6.946, + "args": { + "External id": 231127,"Record function id": 0, "Sequence number": 2757821, "Fwd thread id": 1, "Ev Idx": 1238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115539021.988, "dur": 4.545, + "args": { + "External id": 231128,"Sequence number": 2757821, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1239 + } + }, + { + "ph": "f", "id": 135, "pid": 4183440, "tid": 31337, "ts": 667115539021.988, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115539022.685, "dur": 3.666, + "args": { + "External id": 231129,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115539023.360, "dur": 2.522, + "args": { + "External id": 231130,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115539025.265, "dur": 0.494, + "args": { + "External id": 231131,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115539032.027, "dur": 5.068, + "args": { + "External id": 231132,"Record function id": 0, "Ev Idx": 1243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115539033.620, "dur": 2.968, + "args": { + "External id": 231133,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115539034.357, "dur": 1.905, + "args": { + "External id": 231134,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115539034.842, "dur": 1.272, + "args": { + "External id": 231135,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115539043.345, "dur": 337.937, + "args": { + "External id": 231136,"Record function id": 0, "Sequence number": 2757820, "Fwd thread id": 1, "Ev Idx": 1247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115539044.815, "dur": 307.557, + "args": { + "External id": 231137,"Sequence number": 2757820, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1248 + } + }, + { + "ph": "f", "id": 136, "pid": 4183440, "tid": 31337, "ts": 667115539044.815, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115539078.593, "dur": 2.480, + "args": { + "External id": 231138,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115539079.791, "dur": 1.116, + "args": { + "External id": 231139,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115539094.473, "dur": 5.152, + "args": { + "External id": 231140,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115539108.444, "dur": 2.974, + "args": { + "External id": 231141,"Record function id": 0, "Concrete Inputs": ["[132, 1024]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115539252.016, "dur": 1.696, + "args": { + "External id": 231142,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 1024]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[132, 1024], []], "Ev Idx": 1253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 31337, + "ts": 667115539257.892, "dur": 34.023, + "args": { + "External id": 231143,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[135168, 1024, 1], [], [], []], "Input Dims": [[1, 132, 1024], [], [], []], "Ev Idx": 1254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115539267.177, "dur": 0.737, + "args": { + "External id": 231144,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 1024]", "[1024, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1, 1024], [], [], []], "Ev Idx": 1255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115539297.121, "dur": 31.600, + "args": { + "External id": 231145,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[1, 1024], [], [], [], [], []], "Ev Idx": 1256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115539301.145, "dur": 27.370, + "args": { + "External id": 231146,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], [], []], "Input Dims": [[1, 1024], [], [], [], [], [], []], "Ev Idx": 1257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115539305.558, "dur": 4.018, + "args": { + "External id": 231147,"Record function id": 0, "Concrete Inputs": ["[1, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115539311.185, "dur": 16.851, + "args": { + "External id": 231148,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[1, 1024], [1, 1024], []], "Ev Idx": 1259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 31337, + "ts": 667115539333.094, "dur": 2.725, + "args": { + "External id": 231149,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1]], "Input Dims": [[1, 1024], [1024]], "Ev Idx": 1260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115539334.523, "dur": 1.165, + "args": { + "External id": 231150,"Record function id": 0, "Concrete Inputs": ["", "[1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[1, 1024], []], "Ev Idx": 1261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115539341.647, "dur": 4.535, + "args": { + "External id": 231151,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115539344.947, "dur": 1.124, + "args": { + "External id": 231152,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 31337, + "ts": 667115539361.325, "dur": 16.488, + "args": { + "External id": 231153,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 1264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115539389.956, "dur": 7.626, + "args": { + "External id": 231154,"Record function id": 0, "Ev Idx": 1265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115539392.177, "dur": 4.752, + "args": { + "External id": 231155,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115539393.483, "dur": 2.376, + "args": { + "External id": 231156,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115539394.377, "dur": 1.348, + "args": { + "External id": 231157,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115539401.032, "dur": 4.924, + "args": { + "External id": 231158,"Record function id": 0, "Sequence number": 2757819, "Fwd thread id": 1, "Ev Idx": 1269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115539402.236, "dur": 1.044, + "args": { + "External id": 231159,"Sequence number": 2757819, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1270 + } + }, + { + "ph": "f", "id": 137, "pid": 4183440, "tid": 31337, "ts": 667115539402.236, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115539409.788, "dur": 458.974, + "args": { + "External id": 231160,"Record function id": 0, "Sequence number": 2757818, "Fwd thread id": 1, "Ev Idx": 1271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115539411.400, "dur": 446.525, + "args": { + "External id": 231161,"Sequence number": 2757818, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1272 + } + }, + { + "ph": "f", "id": 138, "pid": 4183440, "tid": 31337, "ts": 667115539411.400, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115539440.924, "dur": 8.334, + "args": { + "External id": 231162,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 4183440, "tid": 31337, + "ts": 667115539446.056, "dur": 2.904, + "args": { + "External id": 231163,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]", "[4096, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[16777216, 4096, 1], [], []], "Input Dims": [[16, 4096, 1024], [], []], "Ev Idx": 1274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115539452.205, "dur": 5.124, + "args": { + "External id": 231164,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 1275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115539453.582, "dur": 3.036, + "args": { + "External id": 231165,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2816, 1], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 1276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115539455.669, "dur": 0.727, + "args": { + "External id": 231166,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 1277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 31337, + "ts": 667115539461.060, "dur": 102.408, + "args": { + "External id": 231167,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [1, 2816], []], "Input Dims": [[65536, 1024], [2816, 1024], []], "Ev Idx": 1278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115539464.632, "dur": 5.229, + "args": { + "External id": 231168,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2816]], "Input Dims": [[2816, 1024]], "Ev Idx": 1279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115539465.360, "dur": 3.982, + "args": { + "External id": 231169,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2816], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 1280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115539466.725, "dur": 2.485, + "args": { + "External id": 231170,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[2816, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2816], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 1281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 31337, + "ts": 667115539471.057, "dur": 91.873, + "args": { + "External id": 231171,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816]], "Ev Idx": 1282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115539472.661, "dur": 89.060, + "args": { + "External id": 231172,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816]], "Ev Idx": 1283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 31337, + "ts": 667115539568.792, "dur": 3.665, + "args": { + "External id": 231173,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [11534336, 2816, 1]], "Input Dims": [[65536, 2816], [16, 4096, 2816]], "Ev Idx": 1284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115539570.275, "dur": 2.038, + "args": { + "External id": 231174,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1], []], "Input Dims": [[65536, 2816], []], "Ev Idx": 1285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115539606.435, "dur": 5.980, + "args": { + "External id": 231175,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2816]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115539613.643, "dur": 2.325, + "args": { + "External id": 231176,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2816]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115539617.675, "dur": 1.643, + "args": { + "External id": 231177,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2816]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115539651.965, "dur": 39.201, + "args": { + "External id": 231178,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 1289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115539688.448, "dur": 2.388, + "args": { + "External id": 231179,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 1290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 4183440, "tid": 31337, + "ts": 667115539715.782, "dur": 121.727, + "args": { + "External id": 231180,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[4096, 1], [2816, 1]], []], "Input Dims": [[], [[65536, 1024], [65536, 2816]], []], "Ev Idx": 1291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 31337, + "ts": 667115539721.514, "dur": 7.459, + "args": { + "External id": 231181,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115539725.682, "dur": 2.488, + "args": { + "External id": 231182,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024, 1]", "[4096, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 1293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115539730.734, "dur": 6.373, + "args": { + "External id": 231183,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1, 1], []], "Input Dims": [[65536, 1024, 1], []], "Ev Idx": 1294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115539734.269, "dur": 2.229, + "args": { + "External id": 231184,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1, 65536]", "[1, 1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1, 1], [], [], []], "Input Dims": [[65536, 1024, 1], [], [], []], "Ev Idx": 1295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 31337, + "ts": 667115539738.655, "dur": 3.125, + "args": { + "External id": 231185,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], []], "Input Dims": [[65536, 2816], []], "Ev Idx": 1296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115539740.814, "dur": 0.624, + "args": { + "External id": 231186,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816, 1]", "[2816, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[65536, 2816], [], [], []], "Ev Idx": 1297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115539743.130, "dur": 2.899, + "args": { + "External id": 231187,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1, 1], []], "Input Dims": [[65536, 2816, 1], []], "Ev Idx": 1298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115539744.942, "dur": 0.688, + "args": { + "External id": 231188,"Record function id": 0, "Concrete Inputs": ["", "[1, 2816, 65536]", "[1, 1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1, 1], [], [], []], "Input Dims": [[65536, 2816, 1], [], [], []], "Ev Idx": 1299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115539749.993, "dur": 3.603, + "args": { + "External id": 231189,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 4096], []], "Input Dims": [[1024, 1, 65536], []], "Ev Idx": 1300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115539752.526, "dur": 0.734, + "args": { + "External id": 231190,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536, 1]", "[1, 4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 4096], [], [], []], "Input Dims": [[1024, 1, 65536], [], [], []], "Ev Idx": 1301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115539754.845, "dur": 6.595, + "args": { + "External id": 231191,"Record function id": 0, "Concrete Inputs": ["", "[1, 1024, 65536]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 4096, 1], []], "Input Dims": [[1024, 65536, 1], []], "Ev Idx": 1302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 4183440, "tid": 31337, + "ts": 667115539758.914, "dur": 2.338, + "args": { + "External id": 231192,"Record function id": 0, "Concrete Inputs": ["", "[1, 1024, 65536]", "[1024, 1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 4096, 1], [], []], "Input Dims": [[1024, 65536, 1], [], []], "Ev Idx": 1303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115539763.821, "dur": 2.370, + "args": { + "External id": 231193,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 2816], []], "Input Dims": [[1, 2816, 65536], []], "Ev Idx": 1304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115539765.568, "dur": 0.330, + "args": { + "External id": 231194,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816, 1]", "[2816, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 2816], [], [], []], "Input Dims": [[1, 2816, 65536], [], [], []], "Ev Idx": 1305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115539767.605, "dur": 3.174, + "args": { + "External id": 231195,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1, 1], []], "Input Dims": [[65536, 2816, 1], []], "Ev Idx": 1306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115539768.572, "dur": 2.078, + "args": { + "External id": 231196,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1, 1], []], "Input Dims": [[65536, 2816, 1], []], "Ev Idx": 1307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115539772.116, "dur": 52.388, + "args": { + "External id": 231197,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1, 4096], [184549376, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816]], "Ev Idx": 1308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115539826.487, "dur": 3.029, + "args": { + "External id": 231198,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2883584, 2816, 1], []], "Input Dims": [[1, 1024, 2816], []], "Ev Idx": 1309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 4183440, "tid": 31337, + "ts": 667115539830.699, "dur": 2.558, + "args": { + "External id": 231199,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 2816, 1], []], "Input Dims": [[1024, 1, 2816], []], "Ev Idx": 1310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115539832.463, "dur": 0.432, + "args": { + "External id": 231200,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816, 1]", "[2816, 1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 2816, 1], [], [], []], "Input Dims": [[1024, 1, 2816], [], [], []], "Ev Idx": 1311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115539835.634, "dur": 0.871, + "args": { + "External id": 231201,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1, 2816], []], "Input Dims": [[1024, 2816, 1], []], "Ev Idx": 1312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115539880.749, "dur": 9.694, + "args": { + "External id": 231202,"Record function id": 0, "Ev Idx": 1313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115539883.176, "dur": 6.536, + "args": { + "External id": 231203,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 1314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115539885.260, "dur": 3.650, + "args": { + "External id": 231204,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 1315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115539886.723, "dur": 2.091, + "args": { + "External id": 231205,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 1316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115539894.355, "dur": 7.385, + "args": { + "External id": 231206,"Record function id": 0, "Sequence number": 2757817, "Fwd thread id": 1, "Ev Idx": 1317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115539895.526, "dur": 3.900, + "args": { + "External id": 231207,"Sequence number": 2757817, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[11534336, 2816, 1]], "Input Dims": [[16, 4096, 2816]], "Ev Idx": 1318 + } + }, + { + "ph": "f", "id": 139, "pid": 4183440, "tid": 31337, "ts": 667115539895.526, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115539897.147, "dur": 2.102, + "args": { + "External id": 231208,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 1319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115539898.383, "dur": 0.767, + "args": { + "External id": 231209,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 1320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115539905.084, "dur": 106.577, + "args": { + "External id": 231210,"Record function id": 0, "Sequence number": 2757816, "Fwd thread id": 1, "Ev Idx": 1321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115539905.913, "dur": 99.844, + "args": { + "External id": 231211,"Sequence number": 2757816, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[65536, 2816]], "Ev Idx": 1322 + } + }, + { + "ph": "f", "id": 140, "pid": 4183440, "tid": 31337, "ts": 667115539905.913, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115539910.828, "dur": 4.421, + "args": { + "External id": 231212,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[65536, 2816]], "Ev Idx": 1323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115539912.219, "dur": 2.501, + "args": { + "External id": 231213,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2816, 1], [], []], "Input Dims": [[65536, 2816], [], []], "Ev Idx": 1324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115539913.781, "dur": 0.809, + "args": { + "External id": 231214,"Record function id": 0, "Concrete Inputs": ["", "[2816, 65536]", "[1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[65536, 2816], [], [], []], "Ev Idx": 1325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115539916.322, "dur": 35.118, + "args": { + "External id": 231215,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024]], "Ev Idx": 1326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115539952.410, "dur": 6.950, + "args": { + "External id": 231216,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115539953.181, "dur": 5.410, + "args": { + "External id": 231217,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 1328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115539957.368, "dur": 1.033, + "args": { + "External id": 231218,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 1329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115539960.717, "dur": 3.182, + "args": { + "External id": 231219,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 1330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115539961.512, "dur": 1.953, + "args": { + "External id": 231220,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 1331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115539962.861, "dur": 0.516, + "args": { + "External id": 231221,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 1332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115539964.459, "dur": 40.214, + "args": { + "External id": 231222,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024]], "Ev Idx": 1333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540016.451, "dur": 8.778, + "args": { + "External id": 231223,"Record function id": 0, "Sequence number": 2757815, "Fwd thread id": 1, "Ev Idx": 1334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540017.548, "dur": 6.248, + "args": { + "External id": 231224,"Sequence number": 2757815, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1335 + } + }, + { + "ph": "f", "id": 141, "pid": 4183440, "tid": 31337, "ts": 667115540017.548, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115540019.048, "dur": 4.615, + "args": { + "External id": 231225,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115540022.283, "dur": 1.286, + "args": { + "External id": 231226,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540028.949, "dur": 7.140, + "args": { + "External id": 231227,"Record function id": 0, "Sequence number": 2757814, "Fwd thread id": 1, "Ev Idx": 1338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540029.688, "dur": 4.611, + "args": { + "External id": 231228,"Sequence number": 2757814, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 1339 + } + }, + { + "ph": "f", "id": 142, "pid": 4183440, "tid": 31337, "ts": 667115540029.688, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115540030.613, "dur": 3.485, + "args": { + "External id": 231229,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 1340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115540031.271, "dur": 2.348, + "args": { + "External id": 231230,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 1341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115540032.769, "dur": 0.766, + "args": { + "External id": 231231,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 1342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115540040.036, "dur": 5.334, + "args": { + "External id": 231232,"Record function id": 0, "Ev Idx": 1343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115540041.565, "dur": 3.226, + "args": { + "External id": 231233,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115540042.545, "dur": 1.958, + "args": { + "External id": 231234,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115540043.264, "dur": 1.161, + "args": { + "External id": 231235,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540048.645, "dur": 8.185, + "args": { + "External id": 231236,"Record function id": 0, "Sequence number": 2757813, "Fwd thread id": 1, "Ev Idx": 1347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540049.990, "dur": 5.125, + "args": { + "External id": 231237,"Sequence number": 2757813, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[11534336, 2816, 1]], "Input Dims": [[16, 4096, 2816]], "Ev Idx": 1348 + } + }, + { + "ph": "f", "id": 143, "pid": 4183440, "tid": 31337, "ts": 667115540049.990, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115540053.125, "dur": 1.850, + "args": { + "External id": 231238,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 1349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115540054.107, "dur": 0.749, + "args": { + "External id": 231239,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 1350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540059.905, "dur": 86.782, + "args": { + "External id": 231240,"Record function id": 0, "Sequence number": 2757812, "Fwd thread id": 1, "Ev Idx": 1351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540060.568, "dur": 79.623, + "args": { + "External id": 231241,"Sequence number": 2757812, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[65536, 2816]], "Ev Idx": 1352 + } + }, + { + "ph": "f", "id": 144, "pid": 4183440, "tid": 31337, "ts": 667115540060.568, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115540062.214, "dur": 4.887, + "args": { + "External id": 231242,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[65536, 2816]], "Ev Idx": 1353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115540062.853, "dur": 3.815, + "args": { + "External id": 231243,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2816, 1], [], []], "Input Dims": [[65536, 2816], [], []], "Ev Idx": 1354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115540065.783, "dur": 0.753, + "args": { + "External id": 231244,"Record function id": 0, "Concrete Inputs": ["", "[2816, 65536]", "[1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[65536, 2816], [], [], []], "Ev Idx": 1355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115540067.607, "dur": 26.853, + "args": { + "External id": 231245,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024]], "Ev Idx": 1356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115540095.474, "dur": 3.833, + "args": { + "External id": 231246,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115540095.885, "dur": 2.829, + "args": { + "External id": 231247,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 1358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115540097.732, "dur": 0.818, + "args": { + "External id": 231248,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 1359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115540100.385, "dur": 6.454, + "args": { + "External id": 231249,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 1360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115540101.291, "dur": 5.115, + "args": { + "External id": 231250,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 1361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115540104.378, "dur": 1.961, + "args": { + "External id": 231251,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 1362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115540107.440, "dur": 31.838, + "args": { + "External id": 231252,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024]], "Ev Idx": 1363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540152.803, "dur": 32.206, + "args": { + "External id": 231253,"Record function id": 0, "Sequence number": 2757811, "Fwd thread id": 1, "Ev Idx": 1364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540153.764, "dur": 5.158, + "args": { + "External id": 231254,"Sequence number": 2757811, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1365 + } + }, + { + "ph": "f", "id": 145, "pid": 4183440, "tid": 31337, "ts": 667115540153.764, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115540155.771, "dur": 3.017, + "args": { + "External id": 231255,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115540157.246, "dur": 1.442, + "args": { + "External id": 231256,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 4183440, "tid": 31337, + "ts": 667115540161.652, "dur": 20.521, + "args": { + "External id": 231257,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 1368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540188.616, "dur": 8.993, + "args": { + "External id": 231258,"Record function id": 0, "Sequence number": 2757810, "Fwd thread id": 1, "Ev Idx": 1369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540189.465, "dur": 6.237, + "args": { + "External id": 231259,"Sequence number": 2757810, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 1370 + } + }, + { + "ph": "f", "id": 146, "pid": 4183440, "tid": 31337, "ts": 667115540189.465, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115540190.101, "dur": 5.387, + "args": { + "External id": 231260,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 2816]], "Ev Idx": 1371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115540191.327, "dur": 3.635, + "args": { + "External id": 231261,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 1372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115540194.102, "dur": 0.697, + "args": { + "External id": 231262,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 1373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115540201.495, "dur": 5.700, + "args": { + "External id": 231263,"Record function id": 0, "Ev Idx": 1374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115540203.168, "dur": 3.516, + "args": { + "External id": 231264,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115540204.253, "dur": 2.187, + "args": { + "External id": 231265,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115540205.120, "dur": 1.221, + "args": { + "External id": 231266,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115540210.946, "dur": 425.454, + "args": { + "External id": 231267,"Record function id": 0, "Sequence number": 2757809, "Fwd thread id": 1, "Ev Idx": 1378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115540216.211, "dur": 383.905, + "args": { + "External id": 231268,"Sequence number": 2757809, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [16777216, 4096, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 1379 + } + }, + { + "ph": "f", "id": 147, "pid": 4183440, "tid": 31337, "ts": 667115540216.211, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183440, "tid": 31337, + "ts": 667115540236.173, "dur": 34.900, + "args": { + "External id": 231269,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 31337, + "ts": 667115540237.650, "dur": 33.235, + "args": { + "External id": 231270,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115540240.739, "dur": 5.821, + "args": { + "External id": 231271,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], [], [], []], "Ev Idx": 1382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115540243.397, "dur": 2.789, + "args": { + "External id": 231272,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 1024]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115540247.675, "dur": 22.785, + "args": { + "External id": 231273,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 1384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115540282.645, "dur": 2.250, + "args": { + "External id": 231274,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115540283.445, "dur": 1.299, + "args": { + "External id": 231275,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115540288.453, "dur": 3.285, + "args": { + "External id": 231276,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115540289.473, "dur": 2.160, + "args": { + "External id": 231277,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115540304.590, "dur": 2.863, + "args": { + "External id": 231278,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115540318.455, "dur": 3.867, + "args": { + "External id": 231279,"Record function id": 0, "Concrete Inputs": ["[132, 1024]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115540465.940, "dur": 3.327, + "args": { + "External id": 231280,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 1024]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[132, 1024], []], "Ev Idx": 1391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 31337, + "ts": 667115540473.592, "dur": 54.220, + "args": { + "External id": 231281,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[135168, 1024, 1], [], [], []], "Input Dims": [[1, 132, 1024], [], [], []], "Ev Idx": 1392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115540481.354, "dur": 0.995, + "args": { + "External id": 231282,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 1024]", "[1024, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1, 1024], [], [], []], "Ev Idx": 1393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115540534.873, "dur": 32.449, + "args": { + "External id": 231283,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[1, 1024], [], [], [], [], []], "Ev Idx": 1394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115540536.393, "dur": 30.711, + "args": { + "External id": 231284,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], [], []], "Input Dims": [[1, 1024], [], [], [], [], [], []], "Ev Idx": 1395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115540541.113, "dur": 4.592, + "args": { + "External id": 231285,"Record function id": 0, "Concrete Inputs": ["[1, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115540549.709, "dur": 16.790, + "args": { + "External id": 231286,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[1, 1024], [1, 1024], []], "Ev Idx": 1397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 31337, + "ts": 667115540572.120, "dur": 3.386, + "args": { + "External id": 231287,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1]], "Input Dims": [[1, 1024], [1024]], "Ev Idx": 1398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115540573.489, "dur": 1.889, + "args": { + "External id": 231288,"Record function id": 0, "Concrete Inputs": ["", "[1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[1, 1024], []], "Ev Idx": 1399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115540582.190, "dur": 2.480, + "args": { + "External id": 231289,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115540583.513, "dur": 1.060, + "args": { + "External id": 231290,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115540587.049, "dur": 4.103, + "args": { + "External id": 231291,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115540588.266, "dur": 2.797, + "args": { + "External id": 231292,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 31337, + "ts": 667115540617.435, "dur": 17.509, + "args": { + "External id": 231293,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 1404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115540648.600, "dur": 45.517, + "args": { + "External id": 231294,"Record function id": 0, "Ev Idx": 1405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115540650.910, "dur": 41.740, + "args": { + "External id": 231295,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115540687.065, "dur": 4.008, + "args": { + "External id": 231296,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115540688.291, "dur": 2.532, + "args": { + "External id": 231297,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540699.981, "dur": 8.554, + "args": { + "External id": 231298,"Record function id": 0, "Sequence number": 2757808, "Fwd thread id": 1, "Ev Idx": 1409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540701.521, "dur": 4.653, + "args": { + "External id": 231299,"Sequence number": 2757808, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1410 + } + }, + { + "ph": "f", "id": 148, "pid": 4183440, "tid": 31337, "ts": 667115540701.521, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115540703.538, "dur": 2.445, + "args": { + "External id": 231300,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115540704.455, "dur": 1.425, + "args": { + "External id": 231301,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540714.164, "dur": 135.042, + "args": { + "External id": 231302,"Record function id": 0, "Sequence number": 2757807, "Fwd thread id": 1, "Ev Idx": 1413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540715.334, "dur": 127.440, + "args": { + "External id": 231303,"Sequence number": 2757807, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1414 + } + }, + { + "ph": "f", "id": 149, "pid": 4183440, "tid": 31337, "ts": 667115540715.334, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115540718.109, "dur": 5.267, + "args": { + "External id": 231304,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115540719.470, "dur": 3.325, + "args": { + "External id": 231305,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[65536, 1024], [], []], "Ev Idx": 1416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115540721.451, "dur": 1.179, + "args": { + "External id": 231306,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 1417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115540724.468, "dur": 68.111, + "args": { + "External id": 231307,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024]], "Ev Idx": 1418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115540793.905, "dur": 7.469, + "args": { + "External id": 231308,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115540796.708, "dur": 4.073, + "args": { + "External id": 231309,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115540798.638, "dur": 1.963, + "args": { + "External id": 231310,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115540802.781, "dur": 4.226, + "args": { + "External id": 231311,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115540803.720, "dur": 2.572, + "args": { + "External id": 231312,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115540805.548, "dur": 0.628, + "args": { + "External id": 231313,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115540807.465, "dur": 34.440, + "args": { + "External id": 231314,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 1425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540853.868, "dur": 10.983, + "args": { + "External id": 231315,"Record function id": 0, "Sequence number": 2757806, "Fwd thread id": 1, "Ev Idx": 1426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540854.744, "dur": 8.070, + "args": { + "External id": 231316,"Sequence number": 2757806, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1427 + } + }, + { + "ph": "f", "id": 150, "pid": 4183440, "tid": 31337, "ts": 667115540854.744, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115540858.078, "dur": 4.588, + "args": { + "External id": 231317,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115540859.165, "dur": 3.375, + "args": { + "External id": 231318,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540868.376, "dur": 6.829, + "args": { + "External id": 231319,"Record function id": 0, "Sequence number": 2757805, "Fwd thread id": 1, "Ev Idx": 1430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540869.109, "dur": 4.465, + "args": { + "External id": 231320,"Sequence number": 2757805, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1431 + } + }, + { + "ph": "f", "id": 151, "pid": 4183440, "tid": 31337, "ts": 667115540869.109, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115540870.018, "dur": 3.356, + "args": { + "External id": 231321,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115540870.906, "dur": 2.024, + "args": { + "External id": 231322,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115540872.331, "dur": 0.474, + "args": { + "External id": 231323,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115540879.325, "dur": 7.430, + "args": { + "External id": 231324,"Record function id": 0, "Ev Idx": 1435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115540881.040, "dur": 5.112, + "args": { + "External id": 231325,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115540882.315, "dur": 3.562, + "args": { + "External id": 231326,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115540884.806, "dur": 0.946, + "args": { + "External id": 231327,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540889.868, "dur": 6.284, + "args": { + "External id": 231328,"Record function id": 0, "Sequence number": 2757804, "Fwd thread id": 1, "Ev Idx": 1439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115540890.914, "dur": 3.502, + "args": { + "External id": 231329,"Sequence number": 2757804, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1440 + } + }, + { + "ph": "f", "id": 152, "pid": 4183440, "tid": 31337, "ts": 667115540890.914, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115540892.321, "dur": 1.958, + "args": { + "External id": 231330,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115540893.060, "dur": 1.121, + "args": { + "External id": 231331,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 4183440, "tid": 31337, + "ts": 667115540900.491, "dur": 268.049, + "args": { + "External id": 231332,"Record function id": 0, "Sequence number": 2757803, "Fwd thread id": 1, "Ev Idx": 1443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 4183440, "tid": 31337, + "ts": 667115540901.751, "dur": 251.755, + "args": { + "External id": 231333,"Sequence number": 2757803, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 1444 + } + }, + { + "ph": "f", "id": 153, "pid": 4183440, "tid": 31337, "ts": 667115540901.751, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115540917.776, "dur": 7.182, + "args": { + "External id": 231334,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 1445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115540920.478, "dur": 4.142, + "args": { + "External id": 231335,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115540926.874, "dur": 3.428, + "args": { + "External id": 231336,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 1447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115540928.599, "dur": 1.504, + "args": { + "External id": 231337,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115540931.874, "dur": 3.482, + "args": { + "External id": 231338,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 1449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115540933.645, "dur": 1.471, + "args": { + "External id": 231339,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115540958.893, "dur": 169.899, + "args": { + "External id": 231340,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115541036.044, "dur": 4.065, + "args": { + "External id": 231341,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115541041.862, "dur": 3.762, + "args": { + "External id": 231342,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 4183440, "tid": 31337, + "ts": 667115541140.558, "dur": 3.370, + "args": { + "External id": 231343,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 1454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 4183440, "tid": 31337, + "ts": 667115541147.074, "dur": 0.943, + "args": { + "External id": 231344,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 1455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 4183440, "tid": 31337, + "ts": 667115541150.177, "dur": 0.921, + "args": { + "External id": 231345,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 1456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115541175.955, "dur": 221.390, + "args": { + "External id": 231346,"Record function id": 0, "Sequence number": 2757802, "Fwd thread id": 1, "Ev Idx": 1457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115541177.510, "dur": 213.798, + "args": { + "External id": 231347,"Sequence number": 2757802, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 1458 + } + }, + { + "ph": "f", "id": 154, "pid": 4183440, "tid": 31337, "ts": 667115541177.510, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 31337, + "ts": 667115541195.488, "dur": 49.837, + "args": { + "External id": 231348,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 1459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115541198.566, "dur": 3.251, + "args": { + "External id": 231349,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115541203.392, "dur": 41.320, + "args": { + "External id": 231350,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], []], "Ev Idx": 1461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115541254.325, "dur": 4.387, + "args": { + "External id": 231351,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 1462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115541256.145, "dur": 2.282, + "args": { + "External id": 231352,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115541403.874, "dur": 168.283, + "args": { + "External id": 231353,"Record function id": 0, "Sequence number": 2757801, "Fwd thread id": 1, "Ev Idx": 1464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115541405.782, "dur": 158.712, + "args": { + "External id": 231354,"Sequence number": 2757801, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 1465 + } + }, + { + "ph": "f", "id": 155, "pid": 4183440, "tid": 31337, "ts": 667115541405.782, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 31337, + "ts": 667115541416.479, "dur": 32.780, + "args": { + "External id": 231355,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 1466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115541418.645, "dur": 2.470, + "args": { + "External id": 231356,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115541421.931, "dur": 26.617, + "args": { + "External id": 231357,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], []], "Ev Idx": 1468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 31337, + "ts": 667115541455.743, "dur": 3.907, + "args": { + "External id": 231358,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 1469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115541457.403, "dur": 1.978, + "args": { + "External id": 231359,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541580.443, "dur": 16.207, + "args": { + "External id": 231360,"Record function id": 0, "Sequence number": 2757800, "Fwd thread id": 1, "Ev Idx": 1471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541581.846, "dur": 12.726, + "args": { + "External id": 231361,"Sequence number": 2757800, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 1472 + } + }, + { + "ph": "f", "id": 156, "pid": 4183440, "tid": 31337, "ts": 667115541581.846, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115541586.410, "dur": 7.866, + "args": { + "External id": 231362,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 1473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115541588.264, "dur": 5.806, + "args": { + "External id": 231363,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 1474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541600.096, "dur": 6.741, + "args": { + "External id": 231364,"Record function id": 0, "Sequence number": 2757799, "Fwd thread id": 1, "Ev Idx": 1475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541601.123, "dur": 3.784, + "args": { + "External id": 231365,"Sequence number": 2757799, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 1476 + } + }, + { + "ph": "f", "id": 157, "pid": 4183440, "tid": 31337, "ts": 667115541601.123, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115541602.395, "dur": 2.348, + "args": { + "External id": 231366,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 1477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115541603.560, "dur": 0.996, + "args": { + "External id": 231367,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 1478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541609.903, "dur": 6.008, + "args": { + "External id": 231368,"Record function id": 0, "Sequence number": 2757798, "Fwd thread id": 1, "Ev Idx": 1479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541610.969, "dur": 3.607, + "args": { + "External id": 231369,"Sequence number": 2757798, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 1480 + } + }, + { + "ph": "f", "id": 158, "pid": 4183440, "tid": 31337, "ts": 667115541610.969, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115541612.285, "dur": 2.146, + "args": { + "External id": 231370,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 1481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115541613.494, "dur": 0.835, + "args": { + "External id": 231371,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 1482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541619.249, "dur": 8.736, + "args": { + "External id": 231372,"Record function id": 0, "Sequence number": 2757797, "Fwd thread id": 1, "Ev Idx": 1483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541620.887, "dur": 4.978, + "args": { + "External id": 231373,"Sequence number": 2757797, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1484 + } + }, + { + "ph": "f", "id": 159, "pid": 4183440, "tid": 31337, "ts": 667115541620.887, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115541623.685, "dur": 2.042, + "args": { + "External id": 231374,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115541624.624, "dur": 0.996, + "args": { + "External id": 231375,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541631.635, "dur": 200.362, + "args": { + "External id": 231376,"Record function id": 0, "Sequence number": 2757796, "Fwd thread id": 1, "Ev Idx": 1487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541632.678, "dur": 191.354, + "args": { + "External id": 231377,"Sequence number": 2757796, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1488 + } + }, + { + "ph": "f", "id": 160, "pid": 4183440, "tid": 31337, "ts": 667115541632.678, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115541636.675, "dur": 9.452, + "args": { + "External id": 231378,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115541639.143, "dur": 6.294, + "args": { + "External id": 231379,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[65536, 1024], [], []], "Ev Idx": 1490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115541643.328, "dur": 1.827, + "args": { + "External id": 231380,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 1491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115541647.917, "dur": 116.082, + "args": { + "External id": 231381,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024]], "Ev Idx": 1492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115541766.795, "dur": 7.300, + "args": { + "External id": 231382,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115541768.200, "dur": 4.934, + "args": { + "External id": 231383,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115541771.043, "dur": 1.851, + "args": { + "External id": 231384,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115541775.948, "dur": 5.640, + "args": { + "External id": 231385,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115541777.620, "dur": 3.456, + "args": { + "External id": 231386,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115541780.563, "dur": 0.403, + "args": { + "External id": 231387,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115541782.232, "dur": 40.882, + "args": { + "External id": 231388,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 1499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541838.973, "dur": 8.147, + "args": { + "External id": 231389,"Record function id": 0, "Sequence number": 2757795, "Fwd thread id": 1, "Ev Idx": 1500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541840.102, "dur": 5.015, + "args": { + "External id": 231390,"Sequence number": 2757795, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1501 + } + }, + { + "ph": "f", "id": 161, "pid": 4183440, "tid": 31337, "ts": 667115541840.102, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115541842.337, "dur": 2.645, + "args": { + "External id": 231391,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115541843.615, "dur": 1.250, + "args": { + "External id": 231392,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541850.518, "dur": 10.600, + "args": { + "External id": 231393,"Record function id": 0, "Sequence number": 2757794, "Fwd thread id": 1, "Ev Idx": 1504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541851.497, "dur": 7.695, + "args": { + "External id": 231394,"Sequence number": 2757794, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1505 + } + }, + { + "ph": "f", "id": 162, "pid": 4183440, "tid": 31337, "ts": 667115541851.497, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115541852.660, "dur": 6.317, + "args": { + "External id": 231395,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115541855.314, "dur": 3.164, + "args": { + "External id": 231396,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115541857.634, "dur": 0.730, + "args": { + "External id": 231397,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115541866.847, "dur": 9.928, + "args": { + "External id": 231398,"Record function id": 0, "Ev Idx": 1509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115541868.822, "dur": 7.199, + "args": { + "External id": 231399,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115541871.530, "dur": 4.093, + "args": { + "External id": 231400,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115541872.901, "dur": 2.596, + "args": { + "External id": 231401,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541880.286, "dur": 6.948, + "args": { + "External id": 231402,"Record function id": 0, "Sequence number": 2757793, "Fwd thread id": 1, "Ev Idx": 1513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541881.952, "dur": 3.398, + "args": { + "External id": 231403,"Sequence number": 2757793, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1514 + } + }, + { + "ph": "f", "id": 163, "pid": 4183440, "tid": 31337, "ts": 667115541881.952, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115541882.947, "dur": 2.260, + "args": { + "External id": 231404,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115541884.054, "dur": 1.011, + "args": { + "External id": 231405,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541892.376, "dur": 94.877, + "args": { + "External id": 231406,"Record function id": 0, "Sequence number": 2757792, "Fwd thread id": 1, "Ev Idx": 1517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541893.190, "dur": 88.885, + "args": { + "External id": 231407,"Sequence number": 2757792, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1518 + } + }, + { + "ph": "f", "id": 164, "pid": 4183440, "tid": 31337, "ts": 667115541893.190, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115541895.703, "dur": 3.452, + "args": { + "External id": 231408,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115541896.313, "dur": 2.392, + "args": { + "External id": 231409,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[65536, 1024], [], []], "Ev Idx": 1520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115541897.943, "dur": 0.646, + "args": { + "External id": 231410,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 1521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115541899.899, "dur": 34.097, + "args": { + "External id": 231411,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024]], "Ev Idx": 1522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115541935.002, "dur": 6.689, + "args": { + "External id": 231412,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115541936.020, "dur": 5.022, + "args": { + "External id": 231413,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115541939.522, "dur": 1.403, + "args": { + "External id": 231414,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115541942.754, "dur": 5.760, + "args": { + "External id": 231415,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115541944.085, "dur": 4.036, + "args": { + "External id": 231416,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115541945.618, "dur": 2.413, + "args": { + "External id": 231417,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115541949.072, "dur": 32.086, + "args": { + "External id": 231418,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 1529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541993.339, "dur": 38.143, + "args": { + "External id": 231419,"Record function id": 0, "Sequence number": 2757791, "Fwd thread id": 1, "Ev Idx": 1530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115541994.132, "dur": 8.797, + "args": { + "External id": 231420,"Sequence number": 2757791, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1531 + } + }, + { + "ph": "f", "id": 165, "pid": 4183440, "tid": 31337, "ts": 667115541994.132, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115541997.355, "dur": 5.434, + "args": { + "External id": 231421,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115542001.480, "dur": 1.149, + "args": { + "External id": 231422,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 4183440, "tid": 31337, + "ts": 667115542006.024, "dur": 22.980, + "args": { + "External id": 231423,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 1534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115542035.163, "dur": 29.572, + "args": { + "External id": 231424,"Record function id": 0, "Sequence number": 2757790, "Fwd thread id": 1, "Ev Idx": 1535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115542056.109, "dur": 6.567, + "args": { + "External id": 231425,"Sequence number": 2757790, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1536 + } + }, + { + "ph": "f", "id": 166, "pid": 4183440, "tid": 31337, "ts": 667115542056.109, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115542056.793, "dur": 5.689, + "args": { + "External id": 231426,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115542057.503, "dur": 4.460, + "args": { + "External id": 231427,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542061.285, "dur": 0.552, + "args": { + "External id": 231428,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115542068.791, "dur": 5.519, + "args": { + "External id": 231429,"Record function id": 0, "Ev Idx": 1540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115542070.445, "dur": 3.283, + "args": { + "External id": 231430,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115542071.364, "dur": 2.067, + "args": { + "External id": 231431,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115542071.820, "dur": 1.503, + "args": { + "External id": 231432,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115542077.631, "dur": 5.716, + "args": { + "External id": 231433,"Record function id": 0, "Sequence number": 2757789, "Fwd thread id": 1, "Ev Idx": 1544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115542078.848, "dur": 2.976, + "args": { + "External id": 231434,"Sequence number": 2757789, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1545 + } + }, + { + "ph": "f", "id": 167, "pid": 4183440, "tid": 31337, "ts": 667115542078.848, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115542079.980, "dur": 1.698, + "args": { + "External id": 231435,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115542080.625, "dur": 0.920, + "args": { + "External id": 231436,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115542086.469, "dur": 89.013, + "args": { + "External id": 231437,"Record function id": 0, "Sequence number": 2757788, "Fwd thread id": 1, "Ev Idx": 1548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115542087.123, "dur": 82.118, + "args": { + "External id": 231438,"Sequence number": 2757788, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1549 + } + }, + { + "ph": "f", "id": 168, "pid": 4183440, "tid": 31337, "ts": 667115542087.123, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115542091.054, "dur": 2.984, + "args": { + "External id": 231439,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115542091.474, "dur": 2.128, + "args": { + "External id": 231440,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[65536, 1024], [], []], "Ev Idx": 1551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542092.908, "dur": 0.558, + "args": { + "External id": 231441,"Record function id": 0, "Concrete Inputs": ["", "[1024, 65536]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 1552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115542094.679, "dur": 34.909, + "args": { + "External id": 231442,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024]], "Ev Idx": 1553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115542130.542, "dur": 4.310, + "args": { + "External id": 231443,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115542131.024, "dur": 3.310, + "args": { + "External id": 231444,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542133.710, "dur": 0.514, + "args": { + "External id": 231445,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115542135.725, "dur": 3.048, + "args": { + "External id": 231446,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115542136.556, "dur": 1.773, + "args": { + "External id": 231447,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542137.842, "dur": 0.416, + "args": { + "External id": 231448,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115542139.183, "dur": 29.304, + "args": { + "External id": 231449,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 1560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115542179.639, "dur": 23.215, + "args": { + "External id": 231450,"Record function id": 0, "Sequence number": 2757787, "Fwd thread id": 1, "Ev Idx": 1561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115542180.540, "dur": 3.906, + "args": { + "External id": 231451,"Sequence number": 2757787, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 1562 + } + }, + { + "ph": "f", "id": 169, "pid": 4183440, "tid": 31337, "ts": 667115542180.540, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115542182.251, "dur": 2.050, + "args": { + "External id": 231452,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115542183.176, "dur": 0.990, + "args": { + "External id": 231453,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 31337, + "ts": 667115542186.690, "dur": 13.880, + "args": { + "External id": 231454,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 1565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115542206.135, "dur": 8.110, + "args": { + "External id": 231455,"Record function id": 0, "Sequence number": 2757786, "Fwd thread id": 1, "Ev Idx": 1566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 4183440, "tid": 31337, + "ts": 667115542208.665, "dur": 4.211, + "args": { + "External id": 231456,"Sequence number": 2757786, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1567 + } + }, + { + "ph": "f", "id": 170, "pid": 4183440, "tid": 31337, "ts": 667115542208.665, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 31337, + "ts": 667115542209.230, "dur": 3.446, + "args": { + "External id": 231457,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 1024]], "Input Dims": [[1024, 1024]], "Ev Idx": 1568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 31337, + "ts": 667115542210.151, "dur": 2.061, + "args": { + "External id": 231458,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 1024], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 1569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542211.577, "dur": 0.534, + "args": { + "External id": 231459,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1024, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1024], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 1570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115542218.086, "dur": 4.644, + "args": { + "External id": 231460,"Record function id": 0, "Ev Idx": 1571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115542219.699, "dur": 2.459, + "args": { + "External id": 231461,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115542220.410, "dur": 1.472, + "args": { + "External id": 231462,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115542220.868, "dur": 0.906, + "args": { + "External id": 231463,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115542226.819, "dur": 356.105, + "args": { + "External id": 231464,"Record function id": 0, "Sequence number": 2757785, "Fwd thread id": 1, "Ev Idx": 1575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115542228.327, "dur": 321.532, + "args": { + "External id": 231465,"Sequence number": 2757785, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1576 + } + }, + { + "ph": "f", "id": 171, "pid": 4183440, "tid": 31337, "ts": 667115542228.327, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115542258.808, "dur": 3.899, + "args": { + "External id": 231466,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115542261.483, "dur": 1.027, + "args": { + "External id": 231467,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 1578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115542276.379, "dur": 5.717, + "args": { + "External id": 231468,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115542291.010, "dur": 2.688, + "args": { + "External id": 231469,"Record function id": 0, "Concrete Inputs": ["[132, 1024]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115542430.694, "dur": 1.683, + "args": { + "External id": 231470,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 1024]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[132, 1024], []], "Ev Idx": 1581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 31337, + "ts": 667115542436.613, "dur": 31.785, + "args": { + "External id": 231471,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[135168, 1024, 1], [], [], []], "Input Dims": [[1, 132, 1024], [], [], []], "Ev Idx": 1582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542446.053, "dur": 0.802, + "args": { + "External id": 231472,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 1024]", "[1024, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1, 1024], [], [], []], "Ev Idx": 1583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115542473.676, "dur": 50.684, + "args": { + "External id": 231473,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[1, 1024], [], [], [], [], []], "Ev Idx": 1584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115542477.616, "dur": 46.540, + "args": { + "External id": 231474,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], [], []], "Input Dims": [[1, 1024], [], [], [], [], [], []], "Ev Idx": 1585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542481.488, "dur": 3.682, + "args": { + "External id": 231475,"Record function id": 0, "Concrete Inputs": ["[1, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115542486.755, "dur": 36.229, + "args": { + "External id": 231476,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[1, 1024], [1, 1024], []], "Ev Idx": 1587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 31337, + "ts": 667115542530.087, "dur": 3.304, + "args": { + "External id": 231477,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1]], "Input Dims": [[1, 1024], [1024]], "Ev Idx": 1588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115542531.526, "dur": 1.770, + "args": { + "External id": 231478,"Record function id": 0, "Concrete Inputs": ["", "[1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[1, 1024], []], "Ev Idx": 1589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 31337, + "ts": 667115542540.711, "dur": 2.266, + "args": { + "External id": 231479,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115542541.961, "dur": 0.929, + "args": { + "External id": 231480,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 1591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 31337, + "ts": 667115542562.894, "dur": 15.605, + "args": { + "External id": 231481,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 1592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115542593.894, "dur": 8.871, + "args": { + "External id": 231482,"Record function id": 0, "Ev Idx": 1593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115542595.930, "dur": 5.938, + "args": { + "External id": 231483,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115542598.154, "dur": 2.803, + "args": { + "External id": 231484,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115542599.211, "dur": 1.620, + "args": { + "External id": 231485,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115542606.983, "dur": 2578.042, + "args": { + "External id": 231486,"Record function id": 0, "Ev Idx": 1597 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.19)", "pid": 4183440, "tid": 31337, + "ts": 667115542636.895, "dur": 937.494, + "args": { + "External id": 231487,"Record function id": 0, "Ev Idx": 1598 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.18", "pid": 4183440, "tid": 31337, + "ts": 667115542699.509, "dur": 867.005, + "args": { + "External id": 231488,"Record function id": 0, "Ev Idx": 1599 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 4183440, "tid": 31337, + "ts": 667115542715.968, "dur": 834.126, + "args": { + "External id": 231489,"Record function id": 0, "Ev Idx": 1600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115542794.255, "dur": 8.410, + "args": { + "External id": 231490,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115542817.962, "dur": 31.554, + "args": { + "External id": 231491,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 1602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542822.413, "dur": 1.387, + "args": { + "External id": 231492,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542825.741, "dur": 2.920, + "args": { + "External id": 231493,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542831.358, "dur": 0.491, + "args": { + "External id": 231494,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542833.022, "dur": 0.298, + "args": { + "External id": 231495,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542834.764, "dur": 0.272, + "args": { + "External id": 231496,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542837.773, "dur": 0.489, + "args": { + "External id": 231497,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542840.051, "dur": 0.347, + "args": { + "External id": 231498,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542841.659, "dur": 1.659, + "args": { + "External id": 231499,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542844.559, "dur": 0.574, + "args": { + "External id": 231500,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115542865.219, "dur": 31.824, + "args": { + "External id": 231501,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 1612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115542931.762, "dur": 108.287, + "args": { + "External id": 231502,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 1613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115542942.010, "dur": 6.017, + "args": { + "External id": 231503,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115542953.001, "dur": 12.110, + "args": { + "External id": 231504,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 1615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115542958.842, "dur": 5.878, + "args": { + "External id": 231505,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 1616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542962.797, "dur": 0.805, + "args": { + "External id": 231506,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 1617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115542971.901, "dur": 27.454, + "args": { + "External id": 231507,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 1618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542974.342, "dur": 0.621, + "args": { + "External id": 231508,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542976.660, "dur": 1.943, + "args": { + "External id": 231509,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542980.066, "dur": 0.487, + "args": { + "External id": 231510,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542981.817, "dur": 0.312, + "args": { + "External id": 231511,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542985.181, "dur": 0.537, + "args": { + "External id": 231512,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542987.000, "dur": 0.334, + "args": { + "External id": 231513,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542988.608, "dur": 1.942, + "args": { + "External id": 231514,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542993.676, "dur": 0.661, + "args": { + "External id": 231515,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115542995.578, "dur": 0.548, + "args": { + "External id": 231516,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115543010.257, "dur": 21.927, + "args": { + "External id": 231517,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 1628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115543095.127, "dur": 340.591, + "args": { + "External id": 231518,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 1629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115543124.057, "dur": 306.983, + "args": { + "External id": 231519,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1630, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115543134.158, "dur": 291.690, + "args": { + "External id": 231520,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 1631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115543455.822, "dur": 2.369, + "args": { + "External id": 231521,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1632, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115543583.119, "dur": 1582.109, + "args": { + "External id": 231522,"Sequence number": 2757784, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1633 + } + }, + { + "ph": "f", "id": 172, "pid": 4183440, "tid": 31337, "ts": 667115543583.119, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115543743.917, "dur": 105.686, + "args": { + "External id": 231523,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 1634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115543894.953, "dur": 37.478, + "args": { + "External id": 231524,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 1635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115543952.195, "dur": 40.084, + "args": { + "External id": 231525,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 1636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115544002.064, "dur": 25.259, + "args": { + "External id": 231526,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 1637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115544033.099, "dur": 31.741, + "args": { + "External id": 231527,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 1638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115544073.561, "dur": 20.291, + "args": { + "External id": 231528,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 1639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115544100.259, "dur": 27.932, + "args": { + "External id": 231529,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 1640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115544155.045, "dur": 22.991, + "args": { + "External id": 231530,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 1641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115544198.594, "dur": 28.481, + "args": { + "External id": 231531,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115544247.758, "dur": 18.209, + "args": { + "External id": 231532,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 1643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115544281.382, "dur": 14.391, + "args": { + "External id": 231533,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 1644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115544307.573, "dur": 35.150, + "args": { + "External id": 231534,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 1645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115544346.133, "dur": 30.001, + "args": { + "External id": 231535,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 1646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115544404.047, "dur": 183.305, + "args": { + "External id": 231536,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115544477.964, "dur": 5.224, + "args": { + "External id": 231537,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115544485.271, "dur": 4.537, + "args": { + "External id": 231538,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115544622.053, "dur": 27.855, + "args": { + "External id": 231539,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115544697.778, "dur": 17.488, + "args": { + "External id": 231540,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115544728.173, "dur": 52.083, + "args": { + "External id": 231541,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 1652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115544785.870, "dur": 31.067, + "args": { + "External id": 231542,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 1653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115544823.464, "dur": 27.193, + "args": { + "External id": 231543,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 1654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115544857.339, "dur": 28.404, + "args": { + "External id": 231544,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 1655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115544891.417, "dur": 26.225, + "args": { + "External id": 231545,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 1656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115544924.831, "dur": 26.754, + "args": { + "External id": 231546,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 1657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115544973.544, "dur": 23.649, + "args": { + "External id": 231547,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 1658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115545016.509, "dur": 24.982, + "args": { + "External id": 231548,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115545058.422, "dur": 16.407, + "args": { + "External id": 231549,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 1660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115545091.148, "dur": 12.822, + "args": { + "External id": 231550,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 1661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115545120.704, "dur": 15.889, + "args": { + "External id": 231551,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 1662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115545206.556, "dur": 14.858, + "args": { + "External id": 231552,"Record function id": 0, "Ev Idx": 1663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115545209.928, "dur": 10.659, + "args": { + "External id": 231553,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115545214.501, "dur": 5.124, + "args": { + "External id": 231554,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115545215.984, "dur": 3.552, + "args": { + "External id": 231555,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115545225.050, "dur": 5.119, + "args": { + "External id": 231556,"Record function id": 0, "Ev Idx": 1667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115545227.009, "dur": 2.648, + "args": { + "External id": 231557,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115545227.766, "dur": 1.327, + "args": { + "External id": 231558,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115545228.378, "dur": 0.631, + "args": { + "External id": 231559,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115545233.509, "dur": 3.838, + "args": { + "External id": 231560,"Record function id": 0, "Ev Idx": 1671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115545234.945, "dur": 1.976, + "args": { + "External id": 231561,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115545235.439, "dur": 1.082, + "args": { + "External id": 231562,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115545235.832, "dur": 0.616, + "args": { + "External id": 231563,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115545240.429, "dur": 5.706, + "args": { + "External id": 231564,"Record function id": 0, "Ev Idx": 1675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115545241.611, "dur": 4.117, + "args": { + "External id": 231565,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 1676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115545242.288, "dur": 3.040, + "args": { + "External id": 231566,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 1677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115545242.776, "dur": 2.452, + "args": { + "External id": 231567,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 1678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115545249.210, "dur": 6.088, + "args": { + "External id": 231568,"Record function id": 0, "Ev Idx": 1679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115545250.476, "dur": 4.372, + "args": { + "External id": 231569,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115545251.329, "dur": 2.945, + "args": { + "External id": 231570,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115545253.348, "dur": 0.826, + "args": { + "External id": 231571,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115545258.381, "dur": 3.737, + "args": { + "External id": 231572,"Record function id": 0, "Ev Idx": 1683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115545259.545, "dur": 2.164, + "args": { + "External id": 231573,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115545260.047, "dur": 1.259, + "args": { + "External id": 231574,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115545260.569, "dur": 0.633, + "args": { + "External id": 231575,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115545265.248, "dur": 3.567, + "args": { + "External id": 231576,"Record function id": 0, "Ev Idx": 1687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115545266.358, "dur": 2.051, + "args": { + "External id": 231577,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115545267.076, "dur": 0.932, + "args": { + "External id": 231578,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115545267.342, "dur": 0.599, + "args": { + "External id": 231579,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115545271.839, "dur": 4.148, + "args": { + "External id": 231580,"Record function id": 0, "Ev Idx": 1691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115545272.845, "dur": 2.735, + "args": { + "External id": 231581,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115545273.520, "dur": 1.497, + "args": { + "External id": 231582,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115545274.247, "dur": 0.705, + "args": { + "External id": 231583,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115545280.100, "dur": 5.610, + "args": { + "External id": 231584,"Record function id": 0, "Ev Idx": 1695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115545281.193, "dur": 4.114, + "args": { + "External id": 231585,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115545281.840, "dur": 3.026, + "args": { + "External id": 231586,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115545284.000, "dur": 0.780, + "args": { + "External id": 231587,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115545289.497, "dur": 58696.165, + "args": { + "External id": 231588,"Record function id": 0, "Sequence number": 2757783, "Fwd thread id": 1, "Ev Idx": 1699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115545291.182, "dur": 58686.286, + "args": { + "External id": 231589,"Sequence number": 2757783, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1700 + } + }, + { + "ph": "f", "id": 173, "pid": 4183440, "tid": 31337, "ts": 667115545291.182, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.19)", "pid": 4183440, "tid": 31337, + "ts": 667115545319.398, "dur": 37.964, + "args": { + "External id": 231590,"Record function id": 0, "Ev Idx": 1701 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.19)", "pid": 4183440, "tid": 31337, + "ts": 667115545364.742, "dur": 65.146, + "args": { + "External id": 231591,"Record function id": 0, "Ev Idx": 1702 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.19)", "pid": 4183440, "tid": 31337, + "ts": 667115545436.675, "dur": 58532.885, + "args": { + "External id": 231592,"Record function id": 0, "Ev Idx": 1703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115545489.463, "dur": 25.554, + "args": { + "External id": 231593,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115545527.036, "dur": 5.118, + "args": { + "External id": 231594,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 1705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115545549.985, "dur": 57644.063, + "args": { + "External id": 231595,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 1706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115545564.274, "dur": 57621.982, + "args": { + "External id": 231596,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 1707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115545597.143, "dur": 7.328, + "args": { + "External id": 231597,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115545609.364, "dur": 57542.123, + "args": { + "External id": 231598,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 1709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115545612.005, "dur": 57538.725, + "args": { + "External id": 231599,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 1710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115545615.940, "dur": 5.651, + "args": { + "External id": 231600,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115545623.344, "dur": 57523.571, + "args": { + "External id": 231601,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 1712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115603284.545, "dur": 9.131, + "args": { + "External id": 231602,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 1713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115603287.258, "dur": 6.090, + "args": { + "External id": 231603,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115603331.044, "dur": 290.565, + "args": { + "External id": 231604,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 1715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115603362.132, "dur": 254.067, + "args": { + "External id": 231605,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1716, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115603374.383, "dur": 236.056, + "args": { + "External id": 231606,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 1717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115603643.702, "dur": 2.229, + "args": { + "External id": 231607,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1718, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115603740.213, "dur": 7.246, + "args": { + "External id": 231608,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115603800.608, "dur": 1.167, + "args": { + "External id": 231609,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115603819.354, "dur": 1.456, + "args": { + "External id": 231610,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115603836.247, "dur": 0.904, + "args": { + "External id": 231611,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115603850.334, "dur": 0.762, + "args": { + "External id": 231612,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115603862.629, "dur": 0.848, + "args": { + "External id": 231613,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115603875.830, "dur": 1.227, + "args": { + "External id": 231614,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115603893.569, "dur": 1.922, + "args": { + "External id": 231615,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115603906.035, "dur": 0.696, + "args": { + "External id": 231616,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115604001.630, "dur": 2647.251, + "args": { + "External id": 231617,"Record function id": 0, "Ev Idx": 1728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.18)", "pid": 4183440, "tid": 31337, + "ts": 667115604019.975, "dur": 1022.227, + "args": { + "External id": 231618,"Record function id": 0, "Ev Idx": 1729 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 4183440, "tid": 31337, + "ts": 667115604036.579, "dur": 297.769, + "args": { + "External id": 231619,"Record function id": 0, "Ev Idx": 1730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115604111.084, "dur": 4.111, + "args": { + "External id": 231620,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 1731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115604118.167, "dur": 1.052, + "args": { + "External id": 231621,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 1732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115604121.214, "dur": 0.792, + "args": { + "External id": 231622,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 1733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115604124.096, "dur": 2.339, + "args": { + "External id": 231623,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 1734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115604129.359, "dur": 0.898, + "args": { + "External id": 231624,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 1735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115604131.604, "dur": 0.915, + "args": { + "External id": 231625,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 1736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115604134.162, "dur": 1.707, + "args": { + "External id": 231626,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 1737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115604137.654, "dur": 0.780, + "args": { + "External id": 231627,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 1738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115604141.859, "dur": 0.843, + "args": { + "External id": 231628,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 1739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115604144.290, "dur": 0.853, + "args": { + "External id": 231629,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 1740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115604163.243, "dur": 143.737, + "args": { + "External id": 231630,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 1741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115604180.528, "dur": 122.303, + "args": { + "External id": 231631,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 1742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115604199.088, "dur": 12.281, + "args": { + "External id": 231632,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115604214.349, "dur": 62.220, + "args": { + "External id": 231633,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 1744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115604216.988, "dur": 59.272, + "args": { + "External id": 231634,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 1745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604220.681, "dur": 6.429, + "args": { + "External id": 231635,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115604230.673, "dur": 45.025, + "args": { + "External id": 231636,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 1747 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.17", "pid": 4183440, "tid": 31337, + "ts": 667115604409.538, "dur": 624.786, + "args": { + "External id": 231637,"Record function id": 0, "Ev Idx": 1748 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 4183440, "tid": 31337, + "ts": 667115604426.605, "dur": 594.180, + "args": { + "External id": 231638,"Record function id": 0, "Ev Idx": 1749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115604478.375, "dur": 4.626, + "args": { + "External id": 231639,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115604516.761, "dur": 34.974, + "args": { + "External id": 231640,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 1751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604521.406, "dur": 2.893, + "args": { + "External id": 231641,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604526.721, "dur": 0.380, + "args": { + "External id": 231642,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604528.483, "dur": 0.444, + "args": { + "External id": 231643,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604532.202, "dur": 0.310, + "args": { + "External id": 231644,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604533.911, "dur": 0.338, + "args": { + "External id": 231645,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604535.875, "dur": 0.481, + "args": { + "External id": 231646,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604539.132, "dur": 2.248, + "args": { + "External id": 231647,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604542.647, "dur": 0.382, + "args": { + "External id": 231648,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604544.663, "dur": 1.554, + "args": { + "External id": 231649,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115604565.203, "dur": 33.401, + "args": { + "External id": 231650,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 1761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115604630.605, "dur": 150.352, + "args": { + "External id": 231651,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 1762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115604641.217, "dur": 4.992, + "args": { + "External id": 231652,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115604685.580, "dur": 11.910, + "args": { + "External id": 231653,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 1764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115604690.548, "dur": 6.492, + "args": { + "External id": 231654,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 1765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604694.646, "dur": 0.832, + "args": { + "External id": 231655,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 1766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115604706.098, "dur": 29.235, + "args": { + "External id": 231656,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 1767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604708.667, "dur": 0.577, + "args": { + "External id": 231657,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604710.901, "dur": 2.108, + "args": { + "External id": 231658,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604714.299, "dur": 0.537, + "args": { + "External id": 231659,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604716.461, "dur": 1.881, + "args": { + "External id": 231660,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604721.345, "dur": 0.373, + "args": { + "External id": 231661,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604723.036, "dur": 0.592, + "args": { + "External id": 231662,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604724.925, "dur": 0.496, + "args": { + "External id": 231663,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604728.506, "dur": 0.379, + "args": { + "External id": 231664,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115604730.098, "dur": 0.535, + "args": { + "External id": 231665,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115604749.297, "dur": 23.792, + "args": { + "External id": 231666,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 1777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115604827.622, "dur": 122.190, + "args": { + "External id": 231667,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 1778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115604857.374, "dur": 89.011, + "args": { + "External id": 231668,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1779, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115604870.653, "dur": 71.938, + "args": { + "External id": 231669,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 1780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115604967.847, "dur": 1.738, + "args": { + "External id": 231670,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1781, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115605049.544, "dur": 1577.482, + "args": { + "External id": 231671,"Sequence number": 2757782, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1782 + } + }, + { + "ph": "f", "id": 174, "pid": 4183440, "tid": 31337, "ts": 667115605049.544, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115605161.416, "dur": 98.244, + "args": { + "External id": 231672,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 1783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115605304.646, "dur": 35.817, + "args": { + "External id": 231673,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 1784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115605356.189, "dur": 39.545, + "args": { + "External id": 231674,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 1785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115605405.011, "dur": 25.798, + "args": { + "External id": 231675,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 1786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115605440.406, "dur": 34.067, + "args": { + "External id": 231676,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 1787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115605480.872, "dur": 41.837, + "args": { + "External id": 231677,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 1788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115605532.433, "dur": 31.234, + "args": { + "External id": 231678,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 1789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115605590.492, "dur": 23.320, + "args": { + "External id": 231679,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 1790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115605633.444, "dur": 62.153, + "args": { + "External id": 231680,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115605723.605, "dur": 19.843, + "args": { + "External id": 231681,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 1792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115605758.947, "dur": 14.946, + "args": { + "External id": 231682,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 1793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115605782.193, "dur": 42.661, + "args": { + "External id": 231683,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 1794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115605828.422, "dur": 30.626, + "args": { + "External id": 231684,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 1795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115605886.835, "dur": 162.364, + "args": { + "External id": 231685,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115605960.748, "dur": 7.202, + "args": { + "External id": 231686,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115605969.804, "dur": 2.235, + "args": { + "External id": 231687,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115606086.631, "dur": 23.794, + "args": { + "External id": 231688,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115606124.813, "dur": 13.791, + "args": { + "External id": 231689,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115606146.613, "dur": 42.471, + "args": { + "External id": 231690,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 1801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115606194.518, "dur": 30.385, + "args": { + "External id": 231691,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 1802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115606234.002, "dur": 28.306, + "args": { + "External id": 231692,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 1803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115606266.645, "dur": 27.338, + "args": { + "External id": 231693,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 1804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115606300.326, "dur": 26.873, + "args": { + "External id": 231694,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 1805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115606333.252, "dur": 26.603, + "args": { + "External id": 231695,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 1806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115606378.535, "dur": 37.383, + "args": { + "External id": 231696,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 1807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115606440.355, "dur": 28.568, + "args": { + "External id": 231697,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115606483.957, "dur": 34.461, + "args": { + "External id": 231698,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 1809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115606541.060, "dur": 19.399, + "args": { + "External id": 231699,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 1810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115606577.266, "dur": 16.278, + "args": { + "External id": 231700,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 1811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115606704.453, "dur": 17.197, + "args": { + "External id": 231701,"Record function id": 0, "Ev Idx": 1812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115606708.297, "dur": 12.116, + "args": { + "External id": 231702,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115606712.967, "dur": 6.037, + "args": { + "External id": 231703,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115606714.459, "dur": 4.309, + "args": { + "External id": 231704,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115606725.590, "dur": 5.356, + "args": { + "External id": 231705,"Record function id": 0, "Ev Idx": 1816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115606727.401, "dur": 3.085, + "args": { + "External id": 231706,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115606728.027, "dur": 1.996, + "args": { + "External id": 231707,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115606728.986, "dur": 0.914, + "args": { + "External id": 231708,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115606734.174, "dur": 5.750, + "args": { + "External id": 231709,"Record function id": 0, "Ev Idx": 1820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115606735.421, "dur": 4.049, + "args": { + "External id": 231710,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115606736.096, "dur": 2.976, + "args": { + "External id": 231711,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115606736.883, "dur": 2.070, + "args": { + "External id": 231712,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115606743.352, "dur": 4.602, + "args": { + "External id": 231713,"Record function id": 0, "Ev Idx": 1824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115606744.698, "dur": 2.825, + "args": { + "External id": 231714,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 1825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115606745.533, "dur": 1.599, + "args": { + "External id": 231715,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 1826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115606746.129, "dur": 0.876, + "args": { + "External id": 231716,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 1827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115606751.305, "dur": 3.967, + "args": { + "External id": 231717,"Record function id": 0, "Ev Idx": 1828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115606752.440, "dur": 2.423, + "args": { + "External id": 231718,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115606753.098, "dur": 1.260, + "args": { + "External id": 231719,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115606753.610, "dur": 0.635, + "args": { + "External id": 231720,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115606758.539, "dur": 3.904, + "args": { + "External id": 231721,"Record function id": 0, "Ev Idx": 1832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115606759.591, "dur": 2.435, + "args": { + "External id": 231722,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115606760.283, "dur": 1.349, + "args": { + "External id": 231723,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115606760.933, "dur": 0.588, + "args": { + "External id": 231724,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115606765.910, "dur": 3.831, + "args": { + "External id": 231725,"Record function id": 0, "Ev Idx": 1836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115606767.270, "dur": 2.051, + "args": { + "External id": 231726,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115606767.986, "dur": 0.946, + "args": { + "External id": 231727,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115606768.284, "dur": 0.538, + "args": { + "External id": 231728,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115606772.821, "dur": 3.814, + "args": { + "External id": 231729,"Record function id": 0, "Ev Idx": 1840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115606773.970, "dur": 2.213, + "args": { + "External id": 231730,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115606774.484, "dur": 1.137, + "args": { + "External id": 231731,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115606774.923, "dur": 0.581, + "args": { + "External id": 231732,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115606779.633, "dur": 5.336, + "args": { + "External id": 231733,"Record function id": 0, "Ev Idx": 1844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115606780.850, "dur": 3.700, + "args": { + "External id": 231734,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115606781.333, "dur": 2.826, + "args": { + "External id": 231735,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115606783.352, "dur": 0.694, + "args": { + "External id": 231736,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115606788.614, "dur": 15360.167, + "args": { + "External id": 231737,"Record function id": 0, "Sequence number": 2757781, "Fwd thread id": 1, "Ev Idx": 1848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115606789.723, "dur": 15351.306, + "args": { + "External id": 231738,"Sequence number": 2757781, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1849 + } + }, + { + "ph": "f", "id": 175, "pid": 4183440, "tid": 31337, "ts": 667115606789.723, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.18)", "pid": 4183440, "tid": 31337, + "ts": 667115606818.611, "dur": 37.102, + "args": { + "External id": 231739,"Record function id": 0, "Ev Idx": 1850 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.18)", "pid": 4183440, "tid": 31337, + "ts": 667115606863.052, "dur": 63.954, + "args": { + "External id": 231740,"Record function id": 0, "Ev Idx": 1851 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.18)", "pid": 4183440, "tid": 31337, + "ts": 667115606933.030, "dur": 15200.855, + "args": { + "External id": 231741,"Record function id": 0, "Ev Idx": 1852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115607021.872, "dur": 7.002, + "args": { + "External id": 231742,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115607038.003, "dur": 6.723, + "args": { + "External id": 231743,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 1854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115607062.890, "dur": 14280.582, + "args": { + "External id": 231744,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 1855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115607076.503, "dur": 14258.643, + "args": { + "External id": 231745,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 1856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115607102.423, "dur": 14.069, + "args": { + "External id": 231746,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115607120.463, "dur": 14178.818, + "args": { + "External id": 231747,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 1858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115607122.828, "dur": 14175.694, + "args": { + "External id": 231748,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 1859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115607128.374, "dur": 4.340, + "args": { + "External id": 231749,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115607134.520, "dur": 14160.247, + "args": { + "External id": 231750,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 1861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115621430.714, "dur": 9.395, + "args": { + "External id": 231751,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 1862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115621433.819, "dur": 5.945, + "args": { + "External id": 231752,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115621469.342, "dur": 346.493, + "args": { + "External id": 231753,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 1864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115621511.332, "dur": 299.113, + "args": { + "External id": 231754,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1865, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115621525.870, "dur": 279.292, + "args": { + "External id": 231755,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 1866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115621837.464, "dur": 2.070, + "args": { + "External id": 231756,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1867, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115621899.406, "dur": 6.315, + "args": { + "External id": 231757,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115621952.421, "dur": 1.314, + "args": { + "External id": 231758,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115621970.780, "dur": 3.014, + "args": { + "External id": 231759,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115621986.990, "dur": 0.909, + "args": { + "External id": 231760,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622002.283, "dur": 1.043, + "args": { + "External id": 231761,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622017.439, "dur": 0.973, + "args": { + "External id": 231762,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622038.218, "dur": 2.405, + "args": { + "External id": 231763,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622056.397, "dur": 2.083, + "args": { + "External id": 231764,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622070.990, "dur": 0.915, + "args": { + "External id": 231765,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115622162.657, "dur": 2656.727, + "args": { + "External id": 231766,"Record function id": 0, "Ev Idx": 1877 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.17)", "pid": 4183440, "tid": 31337, + "ts": 667115622180.859, "dur": 1000.639, + "args": { + "External id": 231767,"Record function id": 0, "Ev Idx": 1878 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 4183440, "tid": 31337, + "ts": 667115622196.657, "dur": 317.813, + "args": { + "External id": 231768,"Record function id": 0, "Ev Idx": 1879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115622273.534, "dur": 3.860, + "args": { + "External id": 231769,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 1880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115622280.808, "dur": 1.100, + "args": { + "External id": 231770,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 1881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115622283.578, "dur": 3.155, + "args": { + "External id": 231771,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 1882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115622288.455, "dur": 1.058, + "args": { + "External id": 231772,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 1883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115622292.485, "dur": 0.739, + "args": { + "External id": 231773,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 1884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115622294.949, "dur": 0.958, + "args": { + "External id": 231774,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 1885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115622297.459, "dur": 1.413, + "args": { + "External id": 231775,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 1886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115622300.447, "dur": 0.905, + "args": { + "External id": 231776,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 1887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115622304.618, "dur": 0.789, + "args": { + "External id": 231777,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 1888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115622307.106, "dur": 0.811, + "args": { + "External id": 231778,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 1889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115622325.532, "dur": 141.094, + "args": { + "External id": 231779,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 1890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115622340.724, "dur": 121.870, + "args": { + "External id": 231780,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 1891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115622356.449, "dur": 14.732, + "args": { + "External id": 231781,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115622374.084, "dur": 61.681, + "args": { + "External id": 231782,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 1893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115622376.602, "dur": 58.898, + "args": { + "External id": 231783,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 1894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622381.015, "dur": 6.119, + "args": { + "External id": 231784,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115622390.520, "dur": 44.359, + "args": { + "External id": 231785,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 1896 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.16", "pid": 4183440, "tid": 31337, + "ts": 667115622596.240, "dur": 578.048, + "args": { + "External id": 231786,"Record function id": 0, "Ev Idx": 1897 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 4183440, "tid": 31337, + "ts": 667115622612.967, "dur": 549.084, + "args": { + "External id": 231787,"Record function id": 0, "Ev Idx": 1898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115622704.069, "dur": 6.799, + "args": { + "External id": 231788,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115622727.345, "dur": 29.730, + "args": { + "External id": 231789,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 1900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622732.018, "dur": 1.442, + "args": { + "External id": 231790,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622735.206, "dur": 1.425, + "args": { + "External id": 231791,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622738.299, "dur": 0.430, + "args": { + "External id": 231792,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622739.676, "dur": 0.537, + "args": { + "External id": 231793,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622742.768, "dur": 0.464, + "args": { + "External id": 231794,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622744.206, "dur": 2.031, + "args": { + "External id": 231795,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622747.338, "dur": 0.338, + "args": { + "External id": 231796,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622749.873, "dur": 0.439, + "args": { + "External id": 231797,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622751.536, "dur": 0.338, + "args": { + "External id": 231798,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115622767.736, "dur": 33.287, + "args": { + "External id": 231799,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 1910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115622831.710, "dur": 104.223, + "args": { + "External id": 231800,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 1911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115622840.603, "dur": 3.414, + "args": { + "External id": 231801,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115622848.402, "dur": 9.701, + "args": { + "External id": 231802,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 1913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115622852.795, "dur": 4.885, + "args": { + "External id": 231803,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 1914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622855.964, "dur": 0.587, + "args": { + "External id": 231804,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 1915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115622864.549, "dur": 33.320, + "args": { + "External id": 231805,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 1916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622866.586, "dur": 0.612, + "args": { + "External id": 231806,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622869.562, "dur": 0.443, + "args": { + "External id": 231807,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622880.969, "dur": 2.204, + "args": { + "External id": 231808,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622884.663, "dur": 1.063, + "args": { + "External id": 231809,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622886.754, "dur": 0.336, + "args": { + "External id": 231810,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622888.539, "dur": 0.343, + "args": { + "External id": 231811,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622891.242, "dur": 0.345, + "args": { + "External id": 231812,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622892.771, "dur": 0.294, + "args": { + "External id": 231813,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115622894.004, "dur": 0.406, + "args": { + "External id": 231814,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 1925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115622908.485, "dur": 20.072, + "args": { + "External id": 231815,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 1926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115622981.345, "dur": 114.524, + "args": { + "External id": 231816,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 1927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115623010.452, "dur": 81.950, + "args": { + "External id": 231817,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1928, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115623020.089, "dur": 68.409, + "args": { + "External id": 231818,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 1929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115623111.668, "dur": 1.972, + "args": { + "External id": 231819,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1930, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115623188.771, "dur": 1610.648, + "args": { + "External id": 231820,"Sequence number": 2757780, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1931 + } + }, + { + "ph": "f", "id": 176, "pid": 4183440, "tid": 31337, "ts": 667115623188.771, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115623296.420, "dur": 97.988, + "args": { + "External id": 231821,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 1932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115623434.256, "dur": 36.836, + "args": { + "External id": 231822,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 1933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115623487.033, "dur": 65.971, + "args": { + "External id": 231823,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 1934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115623567.203, "dur": 28.065, + "args": { + "External id": 231824,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 1935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115623603.158, "dur": 32.965, + "args": { + "External id": 231825,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 1936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115623642.717, "dur": 59.017, + "args": { + "External id": 231826,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 1937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115623716.504, "dur": 32.480, + "args": { + "External id": 231827,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 1938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115623781.031, "dur": 25.918, + "args": { + "External id": 231828,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 1939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115623824.980, "dur": 27.102, + "args": { + "External id": 231829,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115623873.166, "dur": 19.913, + "args": { + "External id": 231830,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 1941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115623906.457, "dur": 15.047, + "args": { + "External id": 231831,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 1942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115623931.341, "dur": 37.361, + "args": { + "External id": 231832,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 1943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115623971.755, "dur": 30.018, + "args": { + "External id": 231833,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 1944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115624030.309, "dur": 164.102, + "args": { + "External id": 231834,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115624104.267, "dur": 8.025, + "args": { + "External id": 231835,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115624114.468, "dur": 2.710, + "args": { + "External id": 231836,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115624224.973, "dur": 23.883, + "args": { + "External id": 231837,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115624261.573, "dur": 15.179, + "args": { + "External id": 231838,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115624284.172, "dur": 41.194, + "args": { + "External id": 231839,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 1950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115624330.733, "dur": 29.729, + "args": { + "External id": 231840,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 1951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115624368.512, "dur": 27.663, + "args": { + "External id": 231841,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 1952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115624400.472, "dur": 27.436, + "args": { + "External id": 231842,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 1953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115624434.058, "dur": 26.751, + "args": { + "External id": 231843,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 1954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115624467.466, "dur": 45.171, + "args": { + "External id": 231844,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 1955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115624535.660, "dur": 25.779, + "args": { + "External id": 231845,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 1956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115624578.945, "dur": 39.600, + "args": { + "External id": 231846,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115624641.341, "dur": 51.818, + "args": { + "External id": 231847,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 1958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115624717.188, "dur": 16.269, + "args": { + "External id": 231848,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 1959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115624750.651, "dur": 17.272, + "args": { + "External id": 231849,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 1960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115624840.260, "dur": 15.374, + "args": { + "External id": 231850,"Record function id": 0, "Ev Idx": 1961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115624843.770, "dur": 10.808, + "args": { + "External id": 231851,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115624848.295, "dur": 5.433, + "args": { + "External id": 231852,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115624849.976, "dur": 3.665, + "args": { + "External id": 231853,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115624859.447, "dur": 5.987, + "args": { + "External id": 231854,"Record function id": 0, "Ev Idx": 1965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115624860.932, "dur": 4.002, + "args": { + "External id": 231855,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115624861.736, "dur": 2.736, + "args": { + "External id": 231856,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115624862.036, "dur": 2.347, + "args": { + "External id": 231857,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115624868.659, "dur": 4.726, + "args": { + "External id": 231858,"Record function id": 0, "Ev Idx": 1969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115624870.326, "dur": 2.614, + "args": { + "External id": 231859,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115624871.060, "dur": 1.480, + "args": { + "External id": 231860,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115624871.581, "dur": 0.843, + "args": { + "External id": 231861,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 1972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115624876.743, "dur": 4.689, + "args": { + "External id": 231862,"Record function id": 0, "Ev Idx": 1973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115624878.012, "dur": 2.984, + "args": { + "External id": 231863,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 1974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115624878.876, "dur": 1.740, + "args": { + "External id": 231864,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 1975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115624879.810, "dur": 0.703, + "args": { + "External id": 231865,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 1976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115624884.792, "dur": 3.686, + "args": { + "External id": 231866,"Record function id": 0, "Ev Idx": 1977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115624885.967, "dur": 2.100, + "args": { + "External id": 231867,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115624886.499, "dur": 1.163, + "args": { + "External id": 231868,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115624886.777, "dur": 0.783, + "args": { + "External id": 231869,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115624891.499, "dur": 3.654, + "args": { + "External id": 231870,"Record function id": 0, "Ev Idx": 1981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115624892.729, "dur": 2.011, + "args": { + "External id": 231871,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115624893.206, "dur": 1.087, + "args": { + "External id": 231872,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115624893.579, "dur": 0.607, + "args": { + "External id": 231873,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115624898.410, "dur": 3.446, + "args": { + "External id": 231874,"Record function id": 0, "Ev Idx": 1985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115624899.449, "dur": 1.999, + "args": { + "External id": 231875,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115624899.963, "dur": 1.097, + "args": { + "External id": 231876,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115624900.269, "dur": 0.692, + "args": { + "External id": 231877,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115624904.929, "dur": 4.881, + "args": { + "External id": 231878,"Record function id": 0, "Ev Idx": 1989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115624905.816, "dur": 3.571, + "args": { + "External id": 231879,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115624906.311, "dur": 2.675, + "args": { + "External id": 231880,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115624908.281, "dur": 0.640, + "args": { + "External id": 231881,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 1992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115624912.810, "dur": 4.889, + "args": { + "External id": 231882,"Record function id": 0, "Ev Idx": 1993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115624913.728, "dur": 3.566, + "args": { + "External id": 231883,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115624914.252, "dur": 2.653, + "args": { + "External id": 231884,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115624914.769, "dur": 2.040, + "args": { + "External id": 231885,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 1996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115624921.128, "dur": 16966.146, + "args": { + "External id": 231886,"Record function id": 0, "Sequence number": 2757779, "Fwd thread id": 1, "Ev Idx": 1997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115624922.333, "dur": 16956.419, + "args": { + "External id": 231887,"Sequence number": 2757779, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 1998 + } + }, + { + "ph": "f", "id": 177, "pid": 4183440, "tid": 31337, "ts": 667115624922.333, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.17)", "pid": 4183440, "tid": 31337, + "ts": 667115624952.764, "dur": 37.588, + "args": { + "External id": 231888,"Record function id": 0, "Ev Idx": 1999 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.17)", "pid": 4183440, "tid": 31337, + "ts": 667115624998.085, "dur": 60.820, + "args": { + "External id": 231889,"Record function id": 0, "Ev Idx": 2000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.17)", "pid": 4183440, "tid": 31337, + "ts": 667115625067.188, "dur": 16804.535, + "args": { + "External id": 231890,"Record function id": 0, "Ev Idx": 2001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115625152.046, "dur": 6.652, + "args": { + "External id": 231891,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115625167.432, "dur": 4.754, + "args": { + "External id": 231892,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 2003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115625185.001, "dur": 15979.286, + "args": { + "External id": 231893,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 2004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115625197.785, "dur": 15957.626, + "args": { + "External id": 231894,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 2005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115625220.176, "dur": 13.396, + "args": { + "External id": 231895,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115625237.834, "dur": 15878.616, + "args": { + "External id": 231896,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 2007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115625239.977, "dur": 15875.578, + "args": { + "External id": 231897,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 2008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115625243.514, "dur": 4.996, + "args": { + "External id": 231898,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115625252.287, "dur": 15859.316, + "args": { + "External id": 231899,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 2010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115641250.698, "dur": 9.383, + "args": { + "External id": 231900,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 2011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115641253.626, "dur": 6.087, + "args": { + "External id": 231901,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115641287.328, "dur": 269.761, + "args": { + "External id": 231902,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 2013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115641315.374, "dur": 237.242, + "args": { + "External id": 231903,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2014, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115641328.499, "dur": 218.781, + "args": { + "External id": 231904,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 2015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115641578.565, "dur": 2.018, + "args": { + "External id": 231905,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2016, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115641635.172, "dur": 5.922, + "args": { + "External id": 231906,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115641717.121, "dur": 3.825, + "args": { + "External id": 231907,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115641737.912, "dur": 1.209, + "args": { + "External id": 231908,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115641750.961, "dur": 0.758, + "args": { + "External id": 231909,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115641762.829, "dur": 0.872, + "args": { + "External id": 231910,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115641773.519, "dur": 2.133, + "args": { + "External id": 231911,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115641785.230, "dur": 1.262, + "args": { + "External id": 231912,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115641797.698, "dur": 2.343, + "args": { + "External id": 231913,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115641811.483, "dur": 0.870, + "args": { + "External id": 231914,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115641901.978, "dur": 2557.622, + "args": { + "External id": 231915,"Record function id": 0, "Ev Idx": 2026 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.16)", "pid": 4183440, "tid": 31337, + "ts": 667115641919.502, "dur": 987.792, + "args": { + "External id": 231916,"Record function id": 0, "Ev Idx": 2027 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 4183440, "tid": 31337, + "ts": 667115641935.347, "dur": 291.964, + "args": { + "External id": 231917,"Record function id": 0, "Ev Idx": 2028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115642008.840, "dur": 5.540, + "args": { + "External id": 231918,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 2029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115642017.302, "dur": 1.204, + "args": { + "External id": 231919,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 2030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115642020.321, "dur": 0.794, + "args": { + "External id": 231920,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115642022.727, "dur": 0.893, + "args": { + "External id": 231921,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115642024.916, "dur": 0.870, + "args": { + "External id": 231922,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115642028.407, "dur": 0.912, + "args": { + "External id": 231923,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115642031.122, "dur": 2.055, + "args": { + "External id": 231924,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 2035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115642034.539, "dur": 0.587, + "args": { + "External id": 231925,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115642036.533, "dur": 2.507, + "args": { + "External id": 231926,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115642041.981, "dur": 0.921, + "args": { + "External id": 231927,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115642059.922, "dur": 139.638, + "args": { + "External id": 231928,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 2039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115642074.900, "dur": 120.774, + "args": { + "External id": 231929,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 2040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115642091.374, "dur": 12.412, + "args": { + "External id": 231930,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115642106.387, "dur": 62.250, + "args": { + "External id": 231931,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 2042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115642109.017, "dur": 59.324, + "args": { + "External id": 231932,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 2043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642114.402, "dur": 6.532, + "args": { + "External id": 231933,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115642122.969, "dur": 44.662, + "args": { + "External id": 231934,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 2045 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.15", "pid": 4183440, "tid": 31337, + "ts": 667115642299.066, "dur": 601.101, + "args": { + "External id": 231935,"Record function id": 0, "Ev Idx": 2046 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 4183440, "tid": 31337, + "ts": 667115642313.955, "dur": 573.110, + "args": { + "External id": 231936,"Record function id": 0, "Ev Idx": 2047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115642386.268, "dur": 4.596, + "args": { + "External id": 231937,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115642405.648, "dur": 24.959, + "args": { + "External id": 231938,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 2049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642409.633, "dur": 1.039, + "args": { + "External id": 231939,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642413.058, "dur": 0.347, + "args": { + "External id": 231940,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642414.252, "dur": 0.298, + "args": { + "External id": 231941,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642415.573, "dur": 3.056, + "args": { + "External id": 231942,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642419.880, "dur": 0.316, + "args": { + "External id": 231943,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642421.190, "dur": 0.247, + "args": { + "External id": 231944,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642423.854, "dur": 0.307, + "args": { + "External id": 231945,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642425.156, "dur": 0.382, + "args": { + "External id": 231946,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642426.264, "dur": 0.311, + "args": { + "External id": 231947,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115642439.362, "dur": 30.372, + "args": { + "External id": 231948,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 2059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115642517.021, "dur": 101.426, + "args": { + "External id": 231949,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 2060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115642527.901, "dur": 4.855, + "args": { + "External id": 231950,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115642537.744, "dur": 11.579, + "args": { + "External id": 231951,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 2062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115642543.163, "dur": 5.727, + "args": { + "External id": 231952,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 2063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642546.151, "dur": 1.133, + "args": { + "External id": 231953,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 2064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115642556.061, "dur": 21.413, + "args": { + "External id": 231954,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 2065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642557.529, "dur": 2.113, + "args": { + "External id": 231955,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642560.427, "dur": 0.710, + "args": { + "External id": 231956,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642561.716, "dur": 0.513, + "args": { + "External id": 231957,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642563.896, "dur": 0.495, + "args": { + "External id": 231958,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642564.993, "dur": 0.389, + "args": { + "External id": 231959,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642566.143, "dur": 1.038, + "args": { + "External id": 231960,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642567.874, "dur": 0.374, + "args": { + "External id": 231961,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642569.136, "dur": 0.497, + "args": { + "External id": 231962,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115642571.190, "dur": 2.119, + "args": { + "External id": 231963,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115642588.516, "dur": 21.880, + "args": { + "External id": 231964,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 2075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115642703.304, "dur": 112.167, + "args": { + "External id": 231965,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 2076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115642729.188, "dur": 82.858, + "args": { + "External id": 231966,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2077, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115642739.281, "dur": 68.811, + "args": { + "External id": 231967,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 2078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115642830.101, "dur": 1.862, + "args": { + "External id": 231968,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2079, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115642914.412, "dur": 1524.002, + "args": { + "External id": 231969,"Sequence number": 2757778, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 2080 + } + }, + { + "ph": "f", "id": 178, "pid": 4183440, "tid": 31337, "ts": 667115642914.412, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115643026.082, "dur": 97.901, + "args": { + "External id": 231970,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 2081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115643163.770, "dur": 36.349, + "args": { + "External id": 231971,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 2082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115643217.532, "dur": 37.277, + "args": { + "External id": 231972,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 2083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115643263.517, "dur": 24.790, + "args": { + "External id": 231973,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 2084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115643295.687, "dur": 31.600, + "args": { + "External id": 231974,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 2085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115643332.983, "dur": 20.292, + "args": { + "External id": 231975,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 2086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115643360.694, "dur": 28.879, + "args": { + "External id": 231976,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 2087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115643413.349, "dur": 19.478, + "args": { + "External id": 231977,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 2088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115643450.906, "dur": 27.465, + "args": { + "External id": 231978,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115643513.039, "dur": 24.763, + "args": { + "External id": 231979,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 2090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115643555.792, "dur": 15.512, + "args": { + "External id": 231980,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 2091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115643580.974, "dur": 38.594, + "args": { + "External id": 231981,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115643623.203, "dur": 66.248, + "args": { + "External id": 231982,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115643725.654, "dur": 176.487, + "args": { + "External id": 231983,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115643804.419, "dur": 7.126, + "args": { + "External id": 231984,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115643813.373, "dur": 2.467, + "args": { + "External id": 231985,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115643933.694, "dur": 24.167, + "args": { + "External id": 231986,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115643968.812, "dur": 12.235, + "args": { + "External id": 231987,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115643988.980, "dur": 47.075, + "args": { + "External id": 231988,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115644043.384, "dur": 30.008, + "args": { + "External id": 231989,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115644079.586, "dur": 28.367, + "args": { + "External id": 231990,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115644112.509, "dur": 26.902, + "args": { + "External id": 231991,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115644144.536, "dur": 26.304, + "args": { + "External id": 231992,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115644177.993, "dur": 29.964, + "args": { + "External id": 231993,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115644228.380, "dur": 25.215, + "args": { + "External id": 231994,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 2105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115644269.099, "dur": 23.871, + "args": { + "External id": 231995,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115644323.054, "dur": 22.677, + "args": { + "External id": 231996,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 2107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115644361.087, "dur": 16.460, + "args": { + "External id": 231997,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 2108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115644389.570, "dur": 16.621, + "args": { + "External id": 231998,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 2109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115644483.500, "dur": 35.372, + "args": { + "External id": 231999,"Record function id": 0, "Ev Idx": 2110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115644486.554, "dur": 30.717, + "args": { + "External id": 232000,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115644490.553, "dur": 25.508, + "args": { + "External id": 232001,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115644509.866, "dur": 5.897, + "args": { + "External id": 232002,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115644524.945, "dur": 10.039, + "args": { + "External id": 232003,"Record function id": 0, "Ev Idx": 2114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115644530.660, "dur": 3.862, + "args": { + "External id": 232004,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115644532.271, "dur": 1.820, + "args": { + "External id": 232005,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115644533.046, "dur": 0.945, + "args": { + "External id": 232006,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115644538.341, "dur": 4.277, + "args": { + "External id": 232007,"Record function id": 0, "Ev Idx": 2118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115644539.468, "dur": 2.743, + "args": { + "External id": 232008,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115644540.239, "dur": 1.584, + "args": { + "External id": 232009,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115644540.823, "dur": 0.852, + "args": { + "External id": 232010,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115644545.791, "dur": 4.231, + "args": { + "External id": 232011,"Record function id": 0, "Ev Idx": 2122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115644546.971, "dur": 2.641, + "args": { + "External id": 232012,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 2123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115644547.983, "dur": 1.245, + "args": { + "External id": 232013,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 2124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115644548.497, "dur": 0.627, + "args": { + "External id": 232014,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 2125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115644553.030, "dur": 5.444, + "args": { + "External id": 232015,"Record function id": 0, "Ev Idx": 2126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115644554.510, "dur": 3.533, + "args": { + "External id": 232016,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115644554.973, "dur": 2.684, + "args": { + "External id": 232017,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115644556.970, "dur": 0.588, + "args": { + "External id": 232018,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115644561.566, "dur": 3.194, + "args": { + "External id": 232019,"Record function id": 0, "Ev Idx": 2130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115644562.522, "dur": 1.824, + "args": { + "External id": 232020,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115644562.987, "dur": 0.991, + "args": { + "External id": 232021,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115644563.272, "dur": 0.617, + "args": { + "External id": 232022,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115644568.151, "dur": 3.628, + "args": { + "External id": 232023,"Record function id": 0, "Ev Idx": 2134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115644569.516, "dur": 1.845, + "args": { + "External id": 232024,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115644569.990, "dur": 0.977, + "args": { + "External id": 232025,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115644570.322, "dur": 0.572, + "args": { + "External id": 232026,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115644574.825, "dur": 5.118, + "args": { + "External id": 232027,"Record function id": 0, "Ev Idx": 2138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115644576.055, "dur": 3.468, + "args": { + "External id": 232028,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115644576.515, "dur": 2.635, + "args": { + "External id": 232029,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115644576.883, "dur": 2.195, + "args": { + "External id": 232030,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115644582.927, "dur": 7.796, + "args": { + "External id": 232031,"Record function id": 0, "Ev Idx": 2142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115644583.930, "dur": 6.377, + "args": { + "External id": 232032,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115644587.391, "dur": 2.547, + "args": { + "External id": 232033,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115644589.160, "dur": 0.684, + "args": { + "External id": 232034,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115644594.290, "dur": 16458.699, + "args": { + "External id": 232035,"Record function id": 0, "Sequence number": 2757777, "Fwd thread id": 1, "Ev Idx": 2146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115644595.472, "dur": 16449.085, + "args": { + "External id": 232036,"Sequence number": 2757777, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 2147 + } + }, + { + "ph": "f", "id": 179, "pid": 4183440, "tid": 31337, "ts": 667115644595.472, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.16)", "pid": 4183440, "tid": 31337, + "ts": 667115644623.502, "dur": 74.251, + "args": { + "External id": 232037,"Record function id": 0, "Ev Idx": 2148 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.16)", "pid": 4183440, "tid": 31337, + "ts": 667115644706.654, "dur": 66.763, + "args": { + "External id": 232038,"Record function id": 0, "Ev Idx": 2149 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.16)", "pid": 4183440, "tid": 31337, + "ts": 667115644779.588, "dur": 16257.812, + "args": { + "External id": 232039,"Record function id": 0, "Ev Idx": 2150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115644866.404, "dur": 10.953, + "args": { + "External id": 232040,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115644888.391, "dur": 4.884, + "args": { + "External id": 232041,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 2152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115644907.907, "dur": 15380.878, + "args": { + "External id": 232042,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 2153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115644922.168, "dur": 15358.709, + "args": { + "External id": 232043,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 2154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115644946.226, "dur": 13.037, + "args": { + "External id": 232044,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115644963.355, "dur": 15281.678, + "args": { + "External id": 232045,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 2156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115644965.731, "dur": 15278.635, + "args": { + "External id": 232046,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 2157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115644971.038, "dur": 4.586, + "args": { + "External id": 232047,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115644977.403, "dur": 15263.522, + "args": { + "External id": 232048,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 2159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115660375.003, "dur": 9.425, + "args": { + "External id": 232049,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 2160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115660378.010, "dur": 6.054, + "args": { + "External id": 232050,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115660414.281, "dur": 338.783, + "args": { + "External id": 232051,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 2162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115660441.399, "dur": 306.683, + "args": { + "External id": 232052,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2163, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115660452.954, "dur": 287.886, + "args": { + "External id": 232053,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 2164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115660774.947, "dur": 2.403, + "args": { + "External id": 232054,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2165, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115660836.368, "dur": 6.234, + "args": { + "External id": 232055,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115660889.215, "dur": 1.455, + "args": { + "External id": 232056,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115660905.928, "dur": 1.375, + "args": { + "External id": 232057,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115660918.088, "dur": 1.213, + "args": { + "External id": 232058,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115660930.475, "dur": 1.027, + "args": { + "External id": 232059,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115660942.406, "dur": 1.204, + "args": { + "External id": 232060,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115660953.566, "dur": 0.893, + "args": { + "External id": 232061,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115660966.642, "dur": 2.576, + "args": { + "External id": 232062,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115660978.318, "dur": 0.626, + "args": { + "External id": 232063,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115661066.716, "dur": 2625.650, + "args": { + "External id": 232064,"Record function id": 0, "Ev Idx": 2175 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.15)", "pid": 4183440, "tid": 31337, + "ts": 667115661085.142, "dur": 970.762, + "args": { + "External id": 232065,"Record function id": 0, "Ev Idx": 2176 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 4183440, "tid": 31337, + "ts": 667115661100.118, "dur": 287.842, + "args": { + "External id": 232066,"Record function id": 0, "Ev Idx": 2177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115661174.438, "dur": 3.890, + "args": { + "External id": 232067,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 2178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115661181.511, "dur": 1.197, + "args": { + "External id": 232068,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 2179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115661184.348, "dur": 1.007, + "args": { + "External id": 232069,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115661187.290, "dur": 1.190, + "args": { + "External id": 232070,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115661190.206, "dur": 0.735, + "args": { + "External id": 232071,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115661193.653, "dur": 0.771, + "args": { + "External id": 232072,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115661195.999, "dur": 1.240, + "args": { + "External id": 232073,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 2184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115661198.599, "dur": 2.669, + "args": { + "External id": 232074,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115661202.541, "dur": 0.854, + "args": { + "External id": 232075,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115661206.179, "dur": 0.775, + "args": { + "External id": 232076,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115661225.319, "dur": 135.184, + "args": { + "External id": 232077,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 2188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115661241.601, "dur": 115.012, + "args": { + "External id": 232078,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 2189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115661254.158, "dur": 13.023, + "args": { + "External id": 232079,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115661269.898, "dur": 58.807, + "args": { + "External id": 232080,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 2191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115661272.337, "dur": 56.033, + "args": { + "External id": 232081,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 2192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661277.398, "dur": 5.528, + "args": { + "External id": 232082,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115661284.390, "dur": 43.291, + "args": { + "External id": 232083,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 2194 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.14", "pid": 4183440, "tid": 31337, + "ts": 667115661457.010, "dur": 591.031, + "args": { + "External id": 232084,"Record function id": 0, "Ev Idx": 2195 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 4183440, "tid": 31337, + "ts": 667115661473.457, "dur": 561.874, + "args": { + "External id": 232085,"Record function id": 0, "Ev Idx": 2196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115661548.902, "dur": 5.744, + "args": { + "External id": 232086,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115661571.119, "dur": 30.829, + "args": { + "External id": 232087,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 2198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661575.619, "dur": 1.651, + "args": { + "External id": 232088,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661579.283, "dur": 0.514, + "args": { + "External id": 232089,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661582.255, "dur": 2.588, + "args": { + "External id": 232090,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661586.259, "dur": 0.489, + "args": { + "External id": 232091,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661587.902, "dur": 1.104, + "args": { + "External id": 232092,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661590.294, "dur": 0.733, + "args": { + "External id": 232093,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661592.446, "dur": 0.461, + "args": { + "External id": 232094,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661595.281, "dur": 0.399, + "args": { + "External id": 232095,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661597.025, "dur": 0.515, + "args": { + "External id": 232096,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115661611.816, "dur": 31.700, + "args": { + "External id": 232097,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 2208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115661711.737, "dur": 106.593, + "args": { + "External id": 232098,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 2209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115661722.797, "dur": 5.017, + "args": { + "External id": 232099,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115661732.947, "dur": 12.870, + "args": { + "External id": 232100,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 2211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115661737.156, "dur": 8.240, + "args": { + "External id": 232101,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 2212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661741.049, "dur": 2.842, + "args": { + "External id": 232102,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 2213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115661752.655, "dur": 24.867, + "args": { + "External id": 232103,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 2214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661755.005, "dur": 0.585, + "args": { + "External id": 232104,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661757.972, "dur": 0.273, + "args": { + "External id": 232105,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661759.701, "dur": 0.525, + "args": { + "External id": 232106,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661761.508, "dur": 0.387, + "args": { + "External id": 232107,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661764.493, "dur": 0.576, + "args": { + "External id": 232108,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661766.327, "dur": 0.568, + "args": { + "External id": 232109,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661768.099, "dur": 1.482, + "args": { + "External id": 232110,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661771.135, "dur": 1.910, + "args": { + "External id": 232111,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115661774.125, "dur": 0.317, + "args": { + "External id": 232112,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115661787.943, "dur": 23.043, + "args": { + "External id": 232113,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 2224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115661862.672, "dur": 110.642, + "args": { + "External id": 232114,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 2225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115661887.449, "dur": 82.596, + "args": { + "External id": 232115,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2226, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115661897.373, "dur": 68.903, + "args": { + "External id": 232116,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 2227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115661987.355, "dur": 1.851, + "args": { + "External id": 232117,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2228, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115662062.284, "dur": 1576.782, + "args": { + "External id": 232118,"Sequence number": 2757776, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 2229 + } + }, + { + "ph": "f", "id": 180, "pid": 4183440, "tid": 31337, "ts": 667115662062.284, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115662170.043, "dur": 97.912, + "args": { + "External id": 232119,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 2230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115662308.831, "dur": 36.372, + "args": { + "External id": 232120,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 2231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115662363.841, "dur": 40.659, + "args": { + "External id": 232121,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 2232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115662413.927, "dur": 26.815, + "args": { + "External id": 232122,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 2233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115662446.798, "dur": 33.571, + "args": { + "External id": 232123,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 2234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115662486.989, "dur": 44.338, + "args": { + "External id": 232124,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 2235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115662543.176, "dur": 30.257, + "args": { + "External id": 232125,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 2236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115662601.602, "dur": 26.051, + "args": { + "External id": 232126,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 2237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115662645.217, "dur": 65.307, + "args": { + "External id": 232127,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115662735.091, "dur": 18.508, + "args": { + "External id": 232128,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 2239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115662766.961, "dur": 16.127, + "args": { + "External id": 232129,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 2240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115662793.454, "dur": 40.311, + "args": { + "External id": 232130,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115662837.403, "dur": 31.248, + "args": { + "External id": 232131,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115662895.036, "dur": 158.553, + "args": { + "External id": 232132,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115662965.807, "dur": 5.433, + "args": { + "External id": 232133,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115662972.988, "dur": 1.962, + "args": { + "External id": 232134,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115663083.699, "dur": 25.660, + "args": { + "External id": 232135,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115663121.294, "dur": 15.178, + "args": { + "External id": 232136,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115663146.081, "dur": 46.398, + "args": { + "External id": 232137,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115663198.509, "dur": 32.849, + "args": { + "External id": 232138,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115663242.088, "dur": 27.572, + "args": { + "External id": 232139,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115663274.126, "dur": 30.205, + "args": { + "External id": 232140,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115663310.491, "dur": 26.720, + "args": { + "External id": 232141,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115663347.222, "dur": 27.865, + "args": { + "External id": 232142,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115663393.774, "dur": 22.025, + "args": { + "External id": 232143,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 2254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115663432.719, "dur": 40.417, + "args": { + "External id": 232144,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115663511.414, "dur": 25.053, + "args": { + "External id": 232145,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 2256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115663556.472, "dur": 18.671, + "args": { + "External id": 232146,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 2257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115663587.327, "dur": 18.061, + "args": { + "External id": 232147,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 2258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115663714.281, "dur": 14.716, + "args": { + "External id": 232148,"Record function id": 0, "Ev Idx": 2259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115663717.380, "dur": 10.681, + "args": { + "External id": 232149,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115663721.548, "dur": 5.359, + "args": { + "External id": 232150,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115663722.923, "dur": 3.901, + "args": { + "External id": 232151,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115663732.919, "dur": 4.603, + "args": { + "External id": 232152,"Record function id": 0, "Ev Idx": 2263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115663734.457, "dur": 2.590, + "args": { + "External id": 232153,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115663735.130, "dur": 1.473, + "args": { + "External id": 232154,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115663735.713, "dur": 0.822, + "args": { + "External id": 232155,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115663740.886, "dur": 5.001, + "args": { + "External id": 232156,"Record function id": 0, "Ev Idx": 2267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115663742.660, "dur": 2.770, + "args": { + "External id": 232157,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115663743.604, "dur": 1.381, + "args": { + "External id": 232158,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115663744.345, "dur": 0.547, + "args": { + "External id": 232159,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115663748.982, "dur": 4.346, + "args": { + "External id": 232160,"Record function id": 0, "Ev Idx": 2271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115663750.389, "dur": 2.484, + "args": { + "External id": 232161,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 2272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115663751.237, "dur": 1.239, + "args": { + "External id": 232162,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 2273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115663751.562, "dur": 0.842, + "args": { + "External id": 232163,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 2274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115663756.281, "dur": 4.575, + "args": { + "External id": 232164,"Record function id": 0, "Ev Idx": 2275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115663757.591, "dur": 2.833, + "args": { + "External id": 232165,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115663758.496, "dur": 1.457, + "args": { + "External id": 232166,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115663759.206, "dur": 0.675, + "args": { + "External id": 232167,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115663763.981, "dur": 3.791, + "args": { + "External id": 232168,"Record function id": 0, "Ev Idx": 2279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115663764.996, "dur": 2.308, + "args": { + "External id": 232169,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115663765.643, "dur": 1.230, + "args": { + "External id": 232170,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115663766.255, "dur": 0.546, + "args": { + "External id": 232171,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115663770.892, "dur": 5.300, + "args": { + "External id": 232172,"Record function id": 0, "Ev Idx": 2283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115663771.949, "dur": 3.811, + "args": { + "External id": 232173,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115663772.422, "dur": 2.933, + "args": { + "External id": 232174,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115663773.167, "dur": 2.117, + "args": { + "External id": 232175,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115663779.151, "dur": 3.576, + "args": { + "External id": 232176,"Record function id": 0, "Ev Idx": 2287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115663780.203, "dur": 2.104, + "args": { + "External id": 232177,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115663780.686, "dur": 1.224, + "args": { + "External id": 232178,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115663781.295, "dur": 0.548, + "args": { + "External id": 232179,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115663785.848, "dur": 3.728, + "args": { + "External id": 232180,"Record function id": 0, "Ev Idx": 2291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115663787.088, "dur": 2.069, + "args": { + "External id": 232181,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115663787.737, "dur": 1.026, + "args": { + "External id": 232182,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115663788.230, "dur": 0.431, + "args": { + "External id": 232183,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115663794.119, "dur": 14726.629, + "args": { + "External id": 232184,"Record function id": 0, "Sequence number": 2757775, "Fwd thread id": 1, "Ev Idx": 2295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115663795.437, "dur": 14715.847, + "args": { + "External id": 232185,"Sequence number": 2757775, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 2296 + } + }, + { + "ph": "f", "id": 181, "pid": 4183440, "tid": 31337, "ts": 667115663795.437, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.15)", "pid": 4183440, "tid": 31337, + "ts": 667115663824.908, "dur": 36.447, + "args": { + "External id": 232186,"Record function id": 0, "Ev Idx": 2297 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.15)", "pid": 4183440, "tid": 31337, + "ts": 667115663868.726, "dur": 67.913, + "args": { + "External id": 232187,"Record function id": 0, "Ev Idx": 2298 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.15)", "pid": 4183440, "tid": 31337, + "ts": 667115663942.961, "dur": 14543.339, + "args": { + "External id": 232188,"Record function id": 0, "Ev Idx": 2299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115664034.116, "dur": 6.893, + "args": { + "External id": 232189,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115664053.342, "dur": 4.905, + "args": { + "External id": 232190,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 2301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115664071.733, "dur": 13782.614, + "args": { + "External id": 232191,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 2302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115664084.756, "dur": 13761.038, + "args": { + "External id": 232192,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 2303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115664106.596, "dur": 13.215, + "args": { + "External id": 232193,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115664123.874, "dur": 13686.337, + "args": { + "External id": 232194,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 2305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115664127.557, "dur": 13681.949, + "args": { + "External id": 232195,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 2306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115664131.412, "dur": 4.629, + "args": { + "External id": 232196,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115664137.752, "dur": 13668.316, + "args": { + "External id": 232197,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 2308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115677941.530, "dur": 9.568, + "args": { + "External id": 232198,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 2309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115677944.437, "dur": 6.236, + "args": { + "External id": 232199,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115677978.000, "dur": 248.648, + "args": { + "External id": 232200,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 2311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115678005.211, "dur": 217.317, + "args": { + "External id": 232201,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2312, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115678016.562, "dur": 201.239, + "args": { + "External id": 232202,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 2313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115678243.957, "dur": 2.069, + "args": { + "External id": 232203,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2314, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115678295.785, "dur": 6.995, + "args": { + "External id": 232204,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115678343.892, "dur": 1.262, + "args": { + "External id": 232205,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115678359.951, "dur": 1.291, + "args": { + "External id": 232206,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115678371.611, "dur": 0.743, + "args": { + "External id": 232207,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115678382.240, "dur": 2.496, + "args": { + "External id": 232208,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115678394.091, "dur": 0.795, + "args": { + "External id": 232209,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115678404.966, "dur": 0.991, + "args": { + "External id": 232210,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115678417.721, "dur": 1.808, + "args": { + "External id": 232211,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115678429.251, "dur": 1.888, + "args": { + "External id": 232212,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115678535.708, "dur": 2613.301, + "args": { + "External id": 232213,"Record function id": 0, "Ev Idx": 2324 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.14)", "pid": 4183440, "tid": 31337, + "ts": 667115678555.550, "dur": 979.997, + "args": { + "External id": 232214,"Record function id": 0, "Ev Idx": 2325 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 4183440, "tid": 31337, + "ts": 667115678570.486, "dur": 334.387, + "args": { + "External id": 232215,"Record function id": 0, "Ev Idx": 2326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115678645.028, "dur": 4.365, + "args": { + "External id": 232216,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 2327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115678687.265, "dur": 1.645, + "args": { + "External id": 232217,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 2328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115678691.664, "dur": 0.805, + "args": { + "External id": 232218,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115678694.425, "dur": 1.007, + "args": { + "External id": 232219,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115678697.359, "dur": 0.992, + "args": { + "External id": 232220,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115678700.115, "dur": 0.577, + "args": { + "External id": 232221,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115678702.316, "dur": 3.197, + "args": { + "External id": 232222,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 2333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115678707.392, "dur": 0.706, + "args": { + "External id": 232223,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115678709.553, "dur": 0.630, + "args": { + "External id": 232224,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115678712.278, "dur": 0.829, + "args": { + "External id": 232225,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115678732.678, "dur": 141.907, + "args": { + "External id": 232226,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 2337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115678748.744, "dur": 121.705, + "args": { + "External id": 232227,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 2338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115678764.280, "dur": 13.058, + "args": { + "External id": 232228,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115678779.971, "dur": 63.333, + "args": { + "External id": 232229,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 2340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115678782.841, "dur": 60.090, + "args": { + "External id": 232230,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 2341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115678787.131, "dur": 7.770, + "args": { + "External id": 232231,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115678796.680, "dur": 45.714, + "args": { + "External id": 232232,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 2343 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.13", "pid": 4183440, "tid": 31337, + "ts": 667115678984.381, "dur": 543.660, + "args": { + "External id": 232233,"Record function id": 0, "Ev Idx": 2344 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 4183440, "tid": 31337, + "ts": 667115679001.053, "dur": 510.045, + "args": { + "External id": 232234,"Record function id": 0, "Ev Idx": 2345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115679054.042, "dur": 4.751, + "args": { + "External id": 232235,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115679074.358, "dur": 30.880, + "args": { + "External id": 232236,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 2347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679079.045, "dur": 2.653, + "args": { + "External id": 232237,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679083.622, "dur": 2.299, + "args": { + "External id": 232238,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679087.221, "dur": 0.344, + "args": { + "External id": 232239,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679090.181, "dur": 0.452, + "args": { + "External id": 232240,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679091.953, "dur": 0.274, + "args": { + "External id": 232241,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679093.682, "dur": 0.529, + "args": { + "External id": 232242,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679096.026, "dur": 0.465, + "args": { + "External id": 232243,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679098.034, "dur": 0.509, + "args": { + "External id": 232244,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679099.956, "dur": 1.720, + "args": { + "External id": 232245,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115679116.328, "dur": 30.825, + "args": { + "External id": 232246,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 2357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115679176.758, "dur": 96.234, + "args": { + "External id": 232247,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 2358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115679185.218, "dur": 5.284, + "args": { + "External id": 232248,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115679195.572, "dur": 9.592, + "args": { + "External id": 232249,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 2360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115679199.702, "dur": 5.033, + "args": { + "External id": 232250,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 2361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679203.149, "dur": 0.604, + "args": { + "External id": 232251,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 2362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115679211.547, "dur": 23.483, + "args": { + "External id": 232252,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 2363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679213.795, "dur": 0.468, + "args": { + "External id": 232253,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679215.890, "dur": 1.181, + "args": { + "External id": 232254,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679218.246, "dur": 0.262, + "args": { + "External id": 232255,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679219.748, "dur": 0.605, + "args": { + "External id": 232256,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679222.337, "dur": 0.371, + "args": { + "External id": 232257,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679223.835, "dur": 0.621, + "args": { + "External id": 232258,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679225.818, "dur": 2.168, + "args": { + "External id": 232259,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679229.571, "dur": 0.273, + "args": { + "External id": 232260,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115679231.017, "dur": 0.407, + "args": { + "External id": 232261,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115679246.212, "dur": 19.986, + "args": { + "External id": 232262,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 2373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115679317.243, "dur": 110.135, + "args": { + "External id": 232263,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 2374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115679342.366, "dur": 81.536, + "args": { + "External id": 232264,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2375, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115679351.925, "dur": 67.924, + "args": { + "External id": 232265,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 2376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115679441.880, "dur": 1.805, + "args": { + "External id": 232266,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2377, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115679542.506, "dur": 1584.060, + "args": { + "External id": 232267,"Sequence number": 2757774, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 2378 + } + }, + { + "ph": "f", "id": 182, "pid": 4183440, "tid": 31337, "ts": 667115679542.506, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115679687.853, "dur": 104.346, + "args": { + "External id": 232268,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 2379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115679836.526, "dur": 37.423, + "args": { + "External id": 232269,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 2380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115679891.824, "dur": 40.639, + "args": { + "External id": 232270,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 2381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115679942.161, "dur": 26.575, + "args": { + "External id": 232271,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 2382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115679974.978, "dur": 32.177, + "args": { + "External id": 232272,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 2383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115680015.750, "dur": 21.944, + "args": { + "External id": 232273,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 2384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115680044.506, "dur": 28.462, + "args": { + "External id": 232274,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 2385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115680096.259, "dur": 23.391, + "args": { + "External id": 232275,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 2386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115680145.650, "dur": 27.265, + "args": { + "External id": 232276,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115680192.904, "dur": 19.226, + "args": { + "External id": 232277,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 2388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115680224.963, "dur": 15.591, + "args": { + "External id": 232278,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 2389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115680249.749, "dur": 36.018, + "args": { + "External id": 232279,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115680289.062, "dur": 29.550, + "args": { + "External id": 232280,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115680342.243, "dur": 181.546, + "args": { + "External id": 232281,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115680413.654, "dur": 6.327, + "args": { + "External id": 232282,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115680422.015, "dur": 3.735, + "args": { + "External id": 232283,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115680557.020, "dur": 26.562, + "args": { + "External id": 232284,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115680594.842, "dur": 16.082, + "args": { + "External id": 232285,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115680619.356, "dur": 84.125, + "args": { + "External id": 232286,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115680711.824, "dur": 37.732, + "args": { + "External id": 232287,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115680756.766, "dur": 27.037, + "args": { + "External id": 232288,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115680789.593, "dur": 29.317, + "args": { + "External id": 232289,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115680824.569, "dur": 26.560, + "args": { + "External id": 232290,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115680857.172, "dur": 27.064, + "args": { + "External id": 232291,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115680905.132, "dur": 27.463, + "args": { + "External id": 232292,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 2403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115680948.896, "dur": 38.121, + "args": { + "External id": 232293,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115681008.862, "dur": 24.475, + "args": { + "External id": 232294,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 2405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115681048.187, "dur": 14.275, + "args": { + "External id": 232295,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 2406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115681078.194, "dur": 21.002, + "args": { + "External id": 232296,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 2407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115681170.464, "dur": 15.087, + "args": { + "External id": 232297,"Record function id": 0, "Ev Idx": 2408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115681173.844, "dur": 10.581, + "args": { + "External id": 232298,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115681178.194, "dur": 5.516, + "args": { + "External id": 232299,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115681179.738, "dur": 3.843, + "args": { + "External id": 232300,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115681189.336, "dur": 4.353, + "args": { + "External id": 232301,"Record function id": 0, "Ev Idx": 2412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115681190.762, "dur": 2.439, + "args": { + "External id": 232302,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115681191.518, "dur": 1.258, + "args": { + "External id": 232303,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115681192.009, "dur": 0.681, + "args": { + "External id": 232304,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115681196.910, "dur": 5.272, + "args": { + "External id": 232305,"Record function id": 0, "Ev Idx": 2416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115681198.503, "dur": 3.246, + "args": { + "External id": 232306,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115681199.796, "dur": 1.562, + "args": { + "External id": 232307,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115681200.564, "dur": 0.711, + "args": { + "External id": 232308,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115681208.034, "dur": 5.918, + "args": { + "External id": 232309,"Record function id": 0, "Ev Idx": 2420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115681209.463, "dur": 4.062, + "args": { + "External id": 232310,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 2421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115681210.371, "dur": 2.760, + "args": { + "External id": 232311,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 2422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115681210.703, "dur": 2.360, + "args": { + "External id": 232312,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 2423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115681217.178, "dur": 3.885, + "args": { + "External id": 232313,"Record function id": 0, "Ev Idx": 2424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115681218.243, "dur": 2.366, + "args": { + "External id": 232314,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115681218.719, "dur": 1.477, + "args": { + "External id": 232315,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115681219.458, "dur": 0.671, + "args": { + "External id": 232316,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115681224.072, "dur": 3.636, + "args": { + "External id": 232317,"Record function id": 0, "Ev Idx": 2428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115681225.133, "dur": 2.149, + "args": { + "External id": 232318,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115681225.659, "dur": 1.156, + "args": { + "External id": 232319,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115681226.135, "dur": 0.605, + "args": { + "External id": 232320,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115681230.862, "dur": 3.806, + "args": { + "External id": 232321,"Record function id": 0, "Ev Idx": 2432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115681231.994, "dur": 2.236, + "args": { + "External id": 232322,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115681232.479, "dur": 1.332, + "args": { + "External id": 232323,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115681233.094, "dur": 0.653, + "args": { + "External id": 232324,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115681237.744, "dur": 3.579, + "args": { + "External id": 232325,"Record function id": 0, "Ev Idx": 2436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115681238.852, "dur": 1.996, + "args": { + "External id": 232326,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115681239.335, "dur": 1.073, + "args": { + "External id": 232327,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115681239.770, "dur": 0.566, + "args": { + "External id": 232328,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115681244.273, "dur": 3.717, + "args": { + "External id": 232329,"Record function id": 0, "Ev Idx": 2440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115681245.414, "dur": 2.147, + "args": { + "External id": 232330,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115681245.917, "dur": 1.221, + "args": { + "External id": 232331,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115681246.467, "dur": 0.597, + "args": { + "External id": 232332,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115681251.936, "dur": 14846.086, + "args": { + "External id": 232333,"Record function id": 0, "Sequence number": 2757773, "Fwd thread id": 1, "Ev Idx": 2444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115681253.776, "dur": 14835.659, + "args": { + "External id": 232334,"Sequence number": 2757773, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 2445 + } + }, + { + "ph": "f", "id": 183, "pid": 4183440, "tid": 31337, "ts": 667115681253.776, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.14)", "pid": 4183440, "tid": 31337, + "ts": 667115681281.935, "dur": 37.069, + "args": { + "External id": 232335,"Record function id": 0, "Ev Idx": 2446 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.14)", "pid": 4183440, "tid": 31337, + "ts": 667115681326.537, "dur": 59.671, + "args": { + "External id": 232336,"Record function id": 0, "Ev Idx": 2447 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.14)", "pid": 4183440, "tid": 31337, + "ts": 667115681392.910, "dur": 14689.126, + "args": { + "External id": 232337,"Record function id": 0, "Ev Idx": 2448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115681482.885, "dur": 6.724, + "args": { + "External id": 232338,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115681518.714, "dur": 4.985, + "args": { + "External id": 232339,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 2450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115681540.346, "dur": 13863.211, + "args": { + "External id": 232340,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 2451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115681553.059, "dur": 13842.492, + "args": { + "External id": 232341,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 2452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115681571.148, "dur": 15.510, + "args": { + "External id": 232342,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115681590.720, "dur": 13770.428, + "args": { + "External id": 232343,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 2454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115681593.265, "dur": 13767.068, + "args": { + "External id": 232344,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 2455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115681597.650, "dur": 5.387, + "args": { + "External id": 232345,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115681604.552, "dur": 13752.368, + "args": { + "External id": 232346,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 2457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115695489.092, "dur": 21.214, + "args": { + "External id": 232347,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 2458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115695502.997, "dur": 6.824, + "args": { + "External id": 232348,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115695539.988, "dur": 281.640, + "args": { + "External id": 232349,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 2460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115695564.612, "dur": 252.169, + "args": { + "External id": 232350,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2461, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115695576.450, "dur": 235.259, + "args": { + "External id": 232351,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 2462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115695840.009, "dur": 2.499, + "args": { + "External id": 232352,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2463, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115695896.755, "dur": 5.955, + "args": { + "External id": 232353,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115695945.389, "dur": 1.706, + "args": { + "External id": 232354,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115695961.356, "dur": 1.465, + "args": { + "External id": 232355,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115695974.679, "dur": 0.888, + "args": { + "External id": 232356,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115695985.699, "dur": 0.749, + "args": { + "External id": 232357,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115695995.409, "dur": 0.882, + "args": { + "External id": 232358,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696005.319, "dur": 0.891, + "args": { + "External id": 232359,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696017.974, "dur": 1.397, + "args": { + "External id": 232360,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696027.342, "dur": 0.809, + "args": { + "External id": 232361,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115696112.171, "dur": 2520.477, + "args": { + "External id": 232362,"Record function id": 0, "Ev Idx": 2473 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.13)", "pid": 4183440, "tid": 31337, + "ts": 667115696130.855, "dur": 953.833, + "args": { + "External id": 232363,"Record function id": 0, "Ev Idx": 2474 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 4183440, "tid": 31337, + "ts": 667115696144.868, "dur": 289.092, + "args": { + "External id": 232364,"Record function id": 0, "Ev Idx": 2475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115696216.746, "dur": 4.067, + "args": { + "External id": 232365,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 2476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115696223.810, "dur": 1.018, + "args": { + "External id": 232366,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 2477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115696226.397, "dur": 0.858, + "args": { + "External id": 232367,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115696228.899, "dur": 2.487, + "args": { + "External id": 232368,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115696232.829, "dur": 0.870, + "args": { + "External id": 232369,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115696235.201, "dur": 0.531, + "args": { + "External id": 232370,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115696237.190, "dur": 1.848, + "args": { + "External id": 232371,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 2482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115696240.549, "dur": 0.861, + "args": { + "External id": 232372,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115696242.907, "dur": 0.794, + "args": { + "External id": 232373,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115696244.868, "dur": 0.912, + "args": { + "External id": 232374,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115696263.968, "dur": 143.768, + "args": { + "External id": 232375,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 2486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115696287.092, "dur": 116.615, + "args": { + "External id": 232376,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 2487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115696300.241, "dur": 13.132, + "args": { + "External id": 232377,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115696315.993, "dur": 61.471, + "args": { + "External id": 232378,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 2489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115696318.396, "dur": 58.740, + "args": { + "External id": 232379,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 2490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696321.901, "dur": 7.400, + "args": { + "External id": 232380,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115696331.130, "dur": 45.333, + "args": { + "External id": 232381,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 2492 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.12", "pid": 4183440, "tid": 31337, + "ts": 667115696526.501, "dur": 551.076, + "args": { + "External id": 232382,"Record function id": 0, "Ev Idx": 2493 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 4183440, "tid": 31337, + "ts": 667115696543.148, "dur": 522.572, + "args": { + "External id": 232383,"Record function id": 0, "Ev Idx": 2494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115696599.071, "dur": 5.728, + "args": { + "External id": 232384,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115696620.696, "dur": 27.240, + "args": { + "External id": 232385,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 2496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696625.203, "dur": 1.415, + "args": { + "External id": 232386,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696628.068, "dur": 0.404, + "args": { + "External id": 232387,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696629.330, "dur": 0.851, + "args": { + "External id": 232388,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696632.434, "dur": 0.562, + "args": { + "External id": 232389,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696633.937, "dur": 0.586, + "args": { + "External id": 232390,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696635.572, "dur": 1.347, + "args": { + "External id": 232391,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696638.125, "dur": 1.948, + "args": { + "External id": 232392,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696641.106, "dur": 0.498, + "args": { + "External id": 232393,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696643.742, "dur": 0.284, + "args": { + "External id": 232394,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115696692.361, "dur": 34.425, + "args": { + "External id": 232395,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 2506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115696759.770, "dur": 95.937, + "args": { + "External id": 232396,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 2507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115696769.957, "dur": 4.376, + "args": { + "External id": 232397,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115696779.656, "dur": 10.134, + "args": { + "External id": 232398,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 2509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115696783.787, "dur": 5.613, + "args": { + "External id": 232399,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 2510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696787.260, "dur": 0.670, + "args": { + "External id": 232400,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 2511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115696796.336, "dur": 23.936, + "args": { + "External id": 232401,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 2512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696798.601, "dur": 0.529, + "args": { + "External id": 232402,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696800.720, "dur": 0.565, + "args": { + "External id": 232403,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696803.438, "dur": 0.441, + "args": { + "External id": 232404,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696805.059, "dur": 2.390, + "args": { + "External id": 232405,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696808.696, "dur": 0.603, + "args": { + "External id": 232406,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696811.258, "dur": 0.409, + "args": { + "External id": 232407,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696812.914, "dur": 0.585, + "args": { + "External id": 232408,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696814.455, "dur": 1.237, + "args": { + "External id": 232409,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115696816.673, "dur": 0.567, + "args": { + "External id": 232410,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115696829.333, "dur": 19.204, + "args": { + "External id": 232411,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 2522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115696899.144, "dur": 105.828, + "args": { + "External id": 232412,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 2523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115696919.804, "dur": 82.046, + "args": { + "External id": 232413,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2524, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115696929.886, "dur": 68.137, + "args": { + "External id": 232414,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 2525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115697017.013, "dur": 1.857, + "args": { + "External id": 232415,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2526, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115697091.599, "dur": 1516.214, + "args": { + "External id": 232416,"Sequence number": 2757772, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 2527 + } + }, + { + "ph": "f", "id": 184, "pid": 4183440, "tid": 31337, "ts": 667115697091.599, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115697197.997, "dur": 98.241, + "args": { + "External id": 232417,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 2528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115697336.346, "dur": 36.256, + "args": { + "External id": 232418,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 2529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115697388.048, "dur": 42.295, + "args": { + "External id": 232419,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 2530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115697439.219, "dur": 27.741, + "args": { + "External id": 232420,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 2531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115697474.689, "dur": 52.933, + "args": { + "External id": 232421,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 2532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115697537.146, "dur": 23.927, + "args": { + "External id": 232422,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 2533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115697567.688, "dur": 28.558, + "args": { + "External id": 232423,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 2534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115697620.420, "dur": 24.536, + "args": { + "External id": 232424,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 2535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115697702.181, "dur": 31.853, + "args": { + "External id": 232425,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115697755.214, "dur": 19.456, + "args": { + "External id": 232426,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 2537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115697785.407, "dur": 15.935, + "args": { + "External id": 232427,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 2538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115697810.869, "dur": 43.938, + "args": { + "External id": 232428,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115697858.076, "dur": 31.476, + "args": { + "External id": 232429,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115697917.592, "dur": 160.744, + "args": { + "External id": 232430,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115697991.231, "dur": 6.349, + "args": { + "External id": 232431,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115697999.488, "dur": 2.554, + "args": { + "External id": 232432,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115698108.302, "dur": 21.775, + "args": { + "External id": 232433,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115698139.541, "dur": 13.841, + "args": { + "External id": 232434,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115698160.791, "dur": 40.327, + "args": { + "External id": 232435,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115698206.647, "dur": 29.931, + "args": { + "External id": 232436,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115698243.811, "dur": 27.342, + "args": { + "External id": 232437,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115698275.178, "dur": 31.088, + "args": { + "External id": 232438,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115698311.451, "dur": 25.561, + "args": { + "External id": 232439,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115698345.799, "dur": 26.718, + "args": { + "External id": 232440,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115698390.009, "dur": 20.399, + "args": { + "External id": 232441,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 2552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115698427.980, "dur": 27.332, + "args": { + "External id": 232442,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115698467.934, "dur": 15.645, + "args": { + "External id": 232443,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 2554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115698520.464, "dur": 17.268, + "args": { + "External id": 232444,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 2555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115698550.905, "dur": 17.559, + "args": { + "External id": 232445,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 2556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115698689.155, "dur": 41.758, + "args": { + "External id": 232446,"Record function id": 0, "Ev Idx": 2557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115698696.534, "dur": 33.065, + "args": { + "External id": 232447,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115698701.078, "dur": 27.326, + "args": { + "External id": 232448,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115698724.100, "dur": 4.027, + "args": { + "External id": 232449,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115698736.126, "dur": 3.792, + "args": { + "External id": 232450,"Record function id": 0, "Ev Idx": 2561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115698737.332, "dur": 2.133, + "args": { + "External id": 232451,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115698737.952, "dur": 1.107, + "args": { + "External id": 232452,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115698738.342, "dur": 0.642, + "args": { + "External id": 232453,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115698743.170, "dur": 9.144, + "args": { + "External id": 232454,"Record function id": 0, "Ev Idx": 2565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115698744.358, "dur": 7.493, + "args": { + "External id": 232455,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115698745.219, "dur": 6.186, + "args": { + "External id": 232456,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115698745.549, "dur": 5.772, + "args": { + "External id": 232457,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115698755.432, "dur": 3.934, + "args": { + "External id": 232458,"Record function id": 0, "Ev Idx": 2569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115698756.720, "dur": 2.229, + "args": { + "External id": 232459,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 2570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115698757.202, "dur": 1.357, + "args": { + "External id": 232460,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 2571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115698757.524, "dur": 0.952, + "args": { + "External id": 232461,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 2572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115698762.310, "dur": 3.414, + "args": { + "External id": 232462,"Record function id": 0, "Ev Idx": 2573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115698763.440, "dur": 1.878, + "args": { + "External id": 232463,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115698763.920, "dur": 1.012, + "args": { + "External id": 232464,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115698764.306, "dur": 0.562, + "args": { + "External id": 232465,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115698768.690, "dur": 3.321, + "args": { + "External id": 232466,"Record function id": 0, "Ev Idx": 2577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115698769.744, "dur": 1.854, + "args": { + "External id": 232467,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115698770.217, "dur": 0.985, + "args": { + "External id": 232468,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115698770.619, "dur": 0.518, + "args": { + "External id": 232469,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115698774.977, "dur": 4.133, + "args": { + "External id": 232470,"Record function id": 0, "Ev Idx": 2581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115698776.196, "dur": 2.501, + "args": { + "External id": 232471,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115698776.818, "dur": 1.477, + "args": { + "External id": 232472,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115698777.595, "dur": 0.628, + "args": { + "External id": 232473,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115698782.351, "dur": 3.906, + "args": { + "External id": 232474,"Record function id": 0, "Ev Idx": 2585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115698783.409, "dur": 2.436, + "args": { + "External id": 232475,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115698783.895, "dur": 1.562, + "args": { + "External id": 232476,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115698784.757, "dur": 0.626, + "args": { + "External id": 232477,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115698789.559, "dur": 3.477, + "args": { + "External id": 232478,"Record function id": 0, "Ev Idx": 2589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115698790.500, "dur": 2.110, + "args": { + "External id": 232479,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115698790.935, "dur": 1.296, + "args": { + "External id": 232480,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115698791.556, "dur": 0.601, + "args": { + "External id": 232481,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115698796.857, "dur": 15054.139, + "args": { + "External id": 232482,"Record function id": 0, "Sequence number": 2757771, "Fwd thread id": 1, "Ev Idx": 2593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115698797.923, "dur": 15044.958, + "args": { + "External id": 232483,"Sequence number": 2757771, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 2594 + } + }, + { + "ph": "f", "id": 185, "pid": 4183440, "tid": 31337, "ts": 667115698797.923, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.13)", "pid": 4183440, "tid": 31337, + "ts": 667115698831.988, "dur": 42.795, + "args": { + "External id": 232484,"Record function id": 0, "Ev Idx": 2595 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.13)", "pid": 4183440, "tid": 31337, + "ts": 667115698882.067, "dur": 62.894, + "args": { + "External id": 232485,"Record function id": 0, "Ev Idx": 2596 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.13)", "pid": 4183440, "tid": 31337, + "ts": 667115698950.882, "dur": 14884.359, + "args": { + "External id": 232486,"Record function id": 0, "Ev Idx": 2597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115699043.102, "dur": 7.324, + "args": { + "External id": 232487,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115699059.498, "dur": 6.192, + "args": { + "External id": 232488,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 2599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115699085.198, "dur": 13988.891, + "args": { + "External id": 232489,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 2600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115699097.996, "dur": 13967.871, + "args": { + "External id": 232490,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 2601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115699116.921, "dur": 13.746, + "args": { + "External id": 232491,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115699135.023, "dur": 13897.071, + "args": { + "External id": 232492,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 2603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115699137.165, "dur": 13894.144, + "args": { + "External id": 232493,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 2604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115699141.095, "dur": 4.906, + "args": { + "External id": 232494,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115699147.586, "dur": 13880.238, + "args": { + "External id": 232495,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 2606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115713158.072, "dur": 9.106, + "args": { + "External id": 232496,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 2607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115713161.063, "dur": 5.786, + "args": { + "External id": 232497,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115713195.494, "dur": 325.051, + "args": { + "External id": 232498,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 2609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115713222.010, "dur": 293.271, + "args": { + "External id": 232499,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2610, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115713232.745, "dur": 276.118, + "args": { + "External id": 232500,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 2611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115713541.600, "dur": 2.449, + "args": { + "External id": 232501,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2612, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115713601.161, "dur": 6.472, + "args": { + "External id": 232502,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115713681.763, "dur": 2.675, + "args": { + "External id": 232503,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115713703.562, "dur": 3.526, + "args": { + "External id": 232504,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115713718.066, "dur": 0.787, + "args": { + "External id": 232505,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115713729.779, "dur": 0.909, + "args": { + "External id": 232506,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115713739.591, "dur": 0.973, + "args": { + "External id": 232507,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115713750.646, "dur": 2.379, + "args": { + "External id": 232508,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115713763.363, "dur": 1.880, + "args": { + "External id": 232509,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115713774.568, "dur": 0.789, + "args": { + "External id": 232510,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115713866.016, "dur": 2569.450, + "args": { + "External id": 232511,"Record function id": 0, "Ev Idx": 2622 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.12)", "pid": 4183440, "tid": 31337, + "ts": 667115713885.085, "dur": 973.558, + "args": { + "External id": 232512,"Record function id": 0, "Ev Idx": 2623 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 4183440, "tid": 31337, + "ts": 667115713900.458, "dur": 289.241, + "args": { + "External id": 232513,"Record function id": 0, "Ev Idx": 2624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115713973.783, "dur": 3.993, + "args": { + "External id": 232514,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 2625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115713980.714, "dur": 1.092, + "args": { + "External id": 232515,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 2626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115713983.893, "dur": 2.526, + "args": { + "External id": 232516,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115713988.700, "dur": 0.894, + "args": { + "External id": 232517,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115713991.394, "dur": 0.892, + "args": { + "External id": 232518,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115713993.810, "dur": 0.657, + "args": { + "External id": 232519,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115713996.300, "dur": 1.605, + "args": { + "External id": 232520,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 2631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115713999.400, "dur": 0.976, + "args": { + "External id": 232521,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115714002.120, "dur": 0.660, + "args": { + "External id": 232522,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115714004.474, "dur": 0.903, + "args": { + "External id": 232523,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115714023.189, "dur": 138.877, + "args": { + "External id": 232524,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 2635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115714039.958, "dur": 118.288, + "args": { + "External id": 232525,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 2636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115714052.206, "dur": 15.331, + "args": { + "External id": 232526,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115714070.190, "dur": 61.930, + "args": { + "External id": 232527,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 2638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115714072.847, "dur": 58.853, + "args": { + "External id": 232528,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 2639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714077.172, "dur": 5.569, + "args": { + "External id": 232529,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115714084.497, "dur": 46.510, + "args": { + "External id": 232530,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 2641 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.11", "pid": 4183440, "tid": 31337, + "ts": 667115714262.799, "dur": 588.662, + "args": { + "External id": 232531,"Record function id": 0, "Ev Idx": 2642 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 4183440, "tid": 31337, + "ts": 667115714279.049, "dur": 559.037, + "args": { + "External id": 232532,"Record function id": 0, "Ev Idx": 2643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115714331.215, "dur": 4.809, + "args": { + "External id": 232533,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115714351.877, "dur": 27.357, + "args": { + "External id": 232534,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 2645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714356.285, "dur": 1.351, + "args": { + "External id": 232535,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714359.407, "dur": 0.424, + "args": { + "External id": 232536,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714361.256, "dur": 1.107, + "args": { + "External id": 232537,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714363.832, "dur": 0.360, + "args": { + "External id": 232538,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714365.596, "dur": 0.336, + "args": { + "External id": 232539,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714367.182, "dur": 2.106, + "args": { + "External id": 232540,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714371.021, "dur": 0.600, + "args": { + "External id": 232541,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714373.183, "dur": 0.333, + "args": { + "External id": 232542,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714374.647, "dur": 0.449, + "args": { + "External id": 232543,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115714387.818, "dur": 28.336, + "args": { + "External id": 232544,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 2655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115714446.024, "dur": 117.945, + "args": { + "External id": 232545,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 2656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115714454.650, "dur": 3.114, + "args": { + "External id": 232546,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115714462.935, "dur": 9.813, + "args": { + "External id": 232547,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 2658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115714467.213, "dur": 5.135, + "args": { + "External id": 232548,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 2659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714470.571, "dur": 0.658, + "args": { + "External id": 232549,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 2660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115714478.490, "dur": 45.932, + "args": { + "External id": 232550,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 2661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714480.268, "dur": 0.630, + "args": { + "External id": 232551,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714482.670, "dur": 0.428, + "args": { + "External id": 232552,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714484.868, "dur": 2.703, + "args": { + "External id": 232553,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714489.396, "dur": 0.351, + "args": { + "External id": 232554,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714511.348, "dur": 0.809, + "args": { + "External id": 232555,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714514.100, "dur": 0.587, + "args": { + "External id": 232556,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714516.564, "dur": 0.412, + "args": { + "External id": 232557,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714518.413, "dur": 0.843, + "args": { + "External id": 232558,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115714520.391, "dur": 0.337, + "args": { + "External id": 232559,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115714537.107, "dur": 19.604, + "args": { + "External id": 232560,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 2671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115714609.772, "dur": 152.780, + "args": { + "External id": 232561,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 2672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115714634.586, "dur": 124.206, + "args": { + "External id": 232562,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2673, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115714643.587, "dur": 110.912, + "args": { + "External id": 232563,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 2674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115714780.230, "dur": 1.774, + "args": { + "External id": 232564,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2675, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115714866.124, "dur": 1551.487, + "args": { + "External id": 232565,"Sequence number": 2757770, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 2676 + } + }, + { + "ph": "f", "id": 186, "pid": 4183440, "tid": 31337, "ts": 667115714866.124, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115714976.647, "dur": 99.028, + "args": { + "External id": 232566,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 2677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115715118.944, "dur": 35.524, + "args": { + "External id": 232567,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 2678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115715170.545, "dur": 41.462, + "args": { + "External id": 232568,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 2679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115715223.157, "dur": 26.803, + "args": { + "External id": 232569,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 2680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115715256.321, "dur": 32.303, + "args": { + "External id": 232570,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 2681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115715295.526, "dur": 20.879, + "args": { + "External id": 232571,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 2682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115715323.698, "dur": 28.591, + "args": { + "External id": 232572,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 2683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115715377.560, "dur": 22.231, + "args": { + "External id": 232573,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 2684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115715418.039, "dur": 28.591, + "args": { + "External id": 232574,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115715465.345, "dur": 19.613, + "args": { + "External id": 232575,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 2686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115715517.333, "dur": 18.228, + "args": { + "External id": 232576,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 2687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115715544.942, "dur": 40.340, + "args": { + "External id": 232577,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115715588.558, "dur": 30.955, + "args": { + "External id": 232578,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115715647.180, "dur": 201.063, + "args": { + "External id": 232579,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115715755.406, "dur": 6.783, + "args": { + "External id": 232580,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115715764.344, "dur": 2.668, + "args": { + "External id": 232581,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115715882.159, "dur": 28.213, + "args": { + "External id": 232582,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115715923.225, "dur": 14.938, + "args": { + "External id": 232583,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115715949.510, "dur": 48.302, + "args": { + "External id": 232584,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115716003.362, "dur": 34.475, + "args": { + "External id": 232585,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115716046.548, "dur": 30.183, + "args": { + "External id": 232586,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115716081.673, "dur": 28.356, + "args": { + "External id": 232587,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115716116.066, "dur": 26.154, + "args": { + "External id": 232588,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115716148.593, "dur": 30.804, + "args": { + "External id": 232589,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115716200.681, "dur": 37.682, + "args": { + "External id": 232590,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 2701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115716263.415, "dur": 27.152, + "args": { + "External id": 232591,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115716305.721, "dur": 16.728, + "args": { + "External id": 232592,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 2703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115716340.996, "dur": 15.643, + "args": { + "External id": 232593,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 2704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115716369.315, "dur": 16.727, + "args": { + "External id": 232594,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 2705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115716457.171, "dur": 14.370, + "args": { + "External id": 232595,"Record function id": 0, "Ev Idx": 2706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115716460.264, "dur": 10.361, + "args": { + "External id": 232596,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115716464.591, "dur": 5.239, + "args": { + "External id": 232597,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115716465.983, "dur": 3.758, + "args": { + "External id": 232598,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115716475.692, "dur": 6.713, + "args": { + "External id": 232599,"Record function id": 0, "Ev Idx": 2710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115716477.266, "dur": 4.653, + "args": { + "External id": 232600,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115716478.109, "dur": 3.339, + "args": { + "External id": 232601,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115716478.624, "dur": 2.757, + "args": { + "External id": 232602,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115716485.771, "dur": 4.451, + "args": { + "External id": 232603,"Record function id": 0, "Ev Idx": 2714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115716487.188, "dur": 2.596, + "args": { + "External id": 232604,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115716488.001, "dur": 1.268, + "args": { + "External id": 232605,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115716488.372, "dur": 0.811, + "args": { + "External id": 232606,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115716513.224, "dur": 6.805, + "args": { + "External id": 232607,"Record function id": 0, "Ev Idx": 2718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115716514.902, "dur": 4.460, + "args": { + "External id": 232608,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 2719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115716516.109, "dur": 2.394, + "args": { + "External id": 232609,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 2720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115716516.986, "dur": 1.333, + "args": { + "External id": 232610,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 2721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115716523.111, "dur": 4.471, + "args": { + "External id": 232611,"Record function id": 0, "Ev Idx": 2722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115716524.172, "dur": 3.009, + "args": { + "External id": 232612,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115716525.163, "dur": 1.496, + "args": { + "External id": 232613,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115716525.761, "dur": 0.823, + "args": { + "External id": 232614,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115716531.336, "dur": 3.955, + "args": { + "External id": 232615,"Record function id": 0, "Ev Idx": 2726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115716532.404, "dur": 2.464, + "args": { + "External id": 232616,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115716533.061, "dur": 1.378, + "args": { + "External id": 232617,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115716533.733, "dur": 0.641, + "args": { + "External id": 232618,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115716538.446, "dur": 3.897, + "args": { + "External id": 232619,"Record function id": 0, "Ev Idx": 2730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115716539.747, "dur": 2.198, + "args": { + "External id": 232620,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115716540.262, "dur": 1.275, + "args": { + "External id": 232621,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115716540.818, "dur": 0.651, + "args": { + "External id": 232622,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115716545.628, "dur": 3.821, + "args": { + "External id": 232623,"Record function id": 0, "Ev Idx": 2734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115716546.672, "dur": 2.376, + "args": { + "External id": 232624,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115716547.185, "dur": 1.439, + "args": { + "External id": 232625,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115716547.949, "dur": 0.610, + "args": { + "External id": 232626,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115716552.620, "dur": 5.349, + "args": { + "External id": 232627,"Record function id": 0, "Ev Idx": 2738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115716553.633, "dur": 3.931, + "args": { + "External id": 232628,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115716554.107, "dur": 3.027, + "args": { + "External id": 232629,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115716554.718, "dur": 2.343, + "args": { + "External id": 232630,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115716561.670, "dur": 14767.122, + "args": { + "External id": 232631,"Record function id": 0, "Sequence number": 2757769, "Fwd thread id": 1, "Ev Idx": 2742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115716562.948, "dur": 14757.720, + "args": { + "External id": 232632,"Sequence number": 2757769, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 2743 + } + }, + { + "ph": "f", "id": 187, "pid": 4183440, "tid": 31337, "ts": 667115716562.948, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.12)", "pid": 4183440, "tid": 31337, + "ts": 667115716592.107, "dur": 40.431, + "args": { + "External id": 232633,"Record function id": 0, "Ev Idx": 2744 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.12)", "pid": 4183440, "tid": 31337, + "ts": 667115716640.039, "dur": 101.968, + "args": { + "External id": 232634,"Record function id": 0, "Ev Idx": 2745 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.12)", "pid": 4183440, "tid": 31337, + "ts": 667115716751.601, "dur": 14561.931, + "args": { + "External id": 232635,"Record function id": 0, "Ev Idx": 2746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115716840.079, "dur": 7.174, + "args": { + "External id": 232636,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115716856.550, "dur": 5.152, + "args": { + "External id": 232637,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 2748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115716876.337, "dur": 13744.903, + "args": { + "External id": 232638,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 2749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115716891.140, "dur": 13722.387, + "args": { + "External id": 232639,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 2750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115716919.432, "dur": 13.845, + "args": { + "External id": 232640,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115716938.443, "dur": 13639.609, + "args": { + "External id": 232641,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 2752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115716940.924, "dur": 13636.375, + "args": { + "External id": 232642,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 2753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115716945.400, "dur": 4.521, + "args": { + "External id": 232643,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115716951.601, "dur": 13622.063, + "args": { + "External id": 232644,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 2755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115730733.365, "dur": 8.945, + "args": { + "External id": 232645,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 2756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115730736.180, "dur": 5.666, + "args": { + "External id": 232646,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115730770.440, "dur": 271.548, + "args": { + "External id": 232647,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 2758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115730797.355, "dur": 239.721, + "args": { + "External id": 232648,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2759, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115730809.576, "dur": 220.123, + "args": { + "External id": 232649,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 2760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115731061.250, "dur": 2.317, + "args": { + "External id": 232650,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2761, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731119.015, "dur": 6.081, + "args": { + "External id": 232651,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731168.505, "dur": 2.855, + "args": { + "External id": 232652,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731185.700, "dur": 1.048, + "args": { + "External id": 232653,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731198.412, "dur": 1.090, + "args": { + "External id": 232654,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731210.424, "dur": 0.959, + "args": { + "External id": 232655,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731221.125, "dur": 2.319, + "args": { + "External id": 232656,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731233.630, "dur": 0.962, + "args": { + "External id": 232657,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731245.229, "dur": 1.984, + "args": { + "External id": 232658,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731256.712, "dur": 0.684, + "args": { + "External id": 232659,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115731342.265, "dur": 2565.907, + "args": { + "External id": 232660,"Record function id": 0, "Ev Idx": 2771 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.11)", "pid": 4183440, "tid": 31337, + "ts": 667115731360.417, "dur": 945.518, + "args": { + "External id": 232661,"Record function id": 0, "Ev Idx": 2772 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 4183440, "tid": 31337, + "ts": 667115731374.951, "dur": 342.824, + "args": { + "External id": 232662,"Record function id": 0, "Ev Idx": 2773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115731446.320, "dur": 5.537, + "args": { + "External id": 232663,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 2774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115731454.844, "dur": 1.093, + "args": { + "External id": 232664,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 2775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115731458.077, "dur": 0.820, + "args": { + "External id": 232665,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115731460.681, "dur": 0.632, + "args": { + "External id": 232666,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115731463.236, "dur": 1.046, + "args": { + "External id": 232667,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115731467.296, "dur": 0.789, + "args": { + "External id": 232668,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115731469.843, "dur": 1.332, + "args": { + "External id": 232669,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 2780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115731472.425, "dur": 0.769, + "args": { + "External id": 232670,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115731475.355, "dur": 2.517, + "args": { + "External id": 232671,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115731479.553, "dur": 0.886, + "args": { + "External id": 232672,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115731513.976, "dur": 135.434, + "args": { + "External id": 232673,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 2784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115731530.304, "dur": 114.760, + "args": { + "External id": 232674,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 2785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115731542.564, "dur": 12.640, + "args": { + "External id": 232675,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115731557.944, "dur": 60.315, + "args": { + "External id": 232676,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 2787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115731560.555, "dur": 57.317, + "args": { + "External id": 232677,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 2788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731564.480, "dur": 6.584, + "args": { + "External id": 232678,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115731572.955, "dur": 44.366, + "args": { + "External id": 232679,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 2790 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.10", "pid": 4183440, "tid": 31337, + "ts": 667115731794.452, "dur": 503.951, + "args": { + "External id": 232680,"Record function id": 0, "Ev Idx": 2791 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 4183440, "tid": 31337, + "ts": 667115731812.503, "dur": 473.658, + "args": { + "External id": 232681,"Record function id": 0, "Ev Idx": 2792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115731866.449, "dur": 5.761, + "args": { + "External id": 232682,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115731887.740, "dur": 28.928, + "args": { + "External id": 232683,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 2794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731892.552, "dur": 1.948, + "args": { + "External id": 232684,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731896.319, "dur": 0.372, + "args": { + "External id": 232685,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731897.697, "dur": 1.625, + "args": { + "External id": 232686,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731900.513, "dur": 2.433, + "args": { + "External id": 232687,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731903.742, "dur": 0.410, + "args": { + "External id": 232688,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731905.873, "dur": 0.561, + "args": { + "External id": 232689,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731907.371, "dur": 0.595, + "args": { + "External id": 232690,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731908.964, "dur": 0.732, + "args": { + "External id": 232691,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115731911.752, "dur": 0.694, + "args": { + "External id": 232692,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115731926.263, "dur": 31.600, + "args": { + "External id": 232693,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 2804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115731987.184, "dur": 87.501, + "args": { + "External id": 232694,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 2805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115731996.674, "dur": 3.227, + "args": { + "External id": 232695,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115732004.573, "dur": 9.376, + "args": { + "External id": 232696,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 2807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115732008.972, "dur": 4.548, + "args": { + "External id": 232697,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 2808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115732011.976, "dur": 0.457, + "args": { + "External id": 232698,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 2809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115732020.334, "dur": 22.087, + "args": { + "External id": 232699,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 2810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115732022.047, "dur": 2.352, + "args": { + "External id": 232700,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115732025.622, "dur": 0.481, + "args": { + "External id": 232701,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115732028.279, "dur": 0.533, + "args": { + "External id": 232702,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115732029.792, "dur": 0.488, + "args": { + "External id": 232703,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115732031.256, "dur": 0.567, + "args": { + "External id": 232704,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115732032.676, "dur": 0.252, + "args": { + "External id": 232705,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115732034.018, "dur": 0.546, + "args": { + "External id": 232706,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115732035.510, "dur": 0.516, + "args": { + "External id": 232707,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115732037.349, "dur": 2.116, + "args": { + "External id": 232708,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115732050.761, "dur": 17.138, + "args": { + "External id": 232709,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 2820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115732115.221, "dur": 108.294, + "args": { + "External id": 232710,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 2821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115732138.611, "dur": 81.487, + "args": { + "External id": 232711,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2822, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115732148.494, "dur": 67.535, + "args": { + "External id": 232712,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 2823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115732237.584, "dur": 1.846, + "args": { + "External id": 232713,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2824, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115732312.666, "dur": 1576.927, + "args": { + "External id": 232714,"Sequence number": 2757768, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 2825 + } + }, + { + "ph": "f", "id": 188, "pid": 4183440, "tid": 31337, "ts": 667115732312.666, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115732417.442, "dur": 120.234, + "args": { + "External id": 232715,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 2826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115732581.832, "dur": 35.903, + "args": { + "External id": 232716,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 2827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115732635.508, "dur": 84.730, + "args": { + "External id": 232717,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 2828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115732734.416, "dur": 29.050, + "args": { + "External id": 232718,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 2829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115732769.917, "dur": 33.900, + "args": { + "External id": 232719,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 2830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115732810.445, "dur": 21.006, + "args": { + "External id": 232720,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 2831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115732840.025, "dur": 29.037, + "args": { + "External id": 232721,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 2832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115732893.770, "dur": 25.318, + "args": { + "External id": 232722,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 2833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115732936.078, "dur": 27.260, + "args": { + "External id": 232723,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115732982.622, "dur": 18.137, + "args": { + "External id": 232724,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 2835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115733012.714, "dur": 14.583, + "args": { + "External id": 232725,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 2836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115733036.611, "dur": 34.501, + "args": { + "External id": 232726,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115733074.268, "dur": 29.311, + "args": { + "External id": 232727,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115733128.589, "dur": 161.921, + "args": { + "External id": 232728,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115733201.563, "dur": 6.013, + "args": { + "External id": 232729,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115733209.612, "dur": 2.950, + "args": { + "External id": 232730,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115733318.922, "dur": 22.125, + "args": { + "External id": 232731,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115733352.584, "dur": 13.214, + "args": { + "External id": 232732,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115733372.605, "dur": 38.692, + "args": { + "External id": 232733,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115733417.952, "dur": 30.864, + "args": { + "External id": 232734,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115733454.887, "dur": 26.870, + "args": { + "External id": 232735,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115733486.243, "dur": 46.832, + "args": { + "External id": 232736,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115733541.402, "dur": 27.357, + "args": { + "External id": 232737,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115733577.104, "dur": 28.069, + "args": { + "External id": 232738,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115733623.423, "dur": 26.049, + "args": { + "External id": 232739,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 2850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115733705.413, "dur": 26.320, + "args": { + "External id": 232740,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115733749.633, "dur": 18.130, + "args": { + "External id": 232741,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 2852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115733799.029, "dur": 24.832, + "args": { + "External id": 232742,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 2853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115733838.666, "dur": 17.987, + "args": { + "External id": 232743,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 2854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115733933.094, "dur": 17.623, + "args": { + "External id": 232744,"Record function id": 0, "Ev Idx": 2855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115733936.929, "dur": 12.807, + "args": { + "External id": 232745,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115733940.980, "dur": 7.870, + "args": { + "External id": 232746,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115733942.637, "dur": 6.083, + "args": { + "External id": 232747,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115733954.594, "dur": 5.277, + "args": { + "External id": 232748,"Record function id": 0, "Ev Idx": 2859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115733956.340, "dur": 3.124, + "args": { + "External id": 232749,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115733957.414, "dur": 1.593, + "args": { + "External id": 232750,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115733957.931, "dur": 0.985, + "args": { + "External id": 232751,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115733963.063, "dur": 4.462, + "args": { + "External id": 232752,"Record function id": 0, "Ev Idx": 2863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115733964.185, "dur": 2.924, + "args": { + "External id": 232753,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115733964.969, "dur": 1.749, + "args": { + "External id": 232754,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115733965.977, "dur": 0.664, + "args": { + "External id": 232755,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 2866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115733970.723, "dur": 7.535, + "args": { + "External id": 232756,"Record function id": 0, "Ev Idx": 2867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115733972.266, "dur": 2.356, + "args": { + "External id": 232757,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 2868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115733972.776, "dur": 1.458, + "args": { + "External id": 232758,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 2869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115733973.378, "dur": 0.743, + "args": { + "External id": 232759,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 2870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115733981.514, "dur": 4.583, + "args": { + "External id": 232760,"Record function id": 0, "Ev Idx": 2871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115733983.122, "dur": 2.516, + "args": { + "External id": 232761,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115733983.789, "dur": 1.427, + "args": { + "External id": 232762,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115733984.487, "dur": 0.636, + "args": { + "External id": 232763,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115733989.512, "dur": 3.706, + "args": { + "External id": 232764,"Record function id": 0, "Ev Idx": 2875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115733990.809, "dur": 1.974, + "args": { + "External id": 232765,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115733991.326, "dur": 1.036, + "args": { + "External id": 232766,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115733991.749, "dur": 0.511, + "args": { + "External id": 232767,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115733996.745, "dur": 3.450, + "args": { + "External id": 232768,"Record function id": 0, "Ev Idx": 2879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115733997.834, "dur": 1.963, + "args": { + "External id": 232769,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115733998.347, "dur": 1.062, + "args": { + "External id": 232770,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115733998.858, "dur": 0.450, + "args": { + "External id": 232771,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115734003.295, "dur": 5.640, + "args": { + "External id": 232772,"Record function id": 0, "Ev Idx": 2883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115734004.225, "dur": 4.286, + "args": { + "External id": 232773,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115734004.688, "dur": 3.410, + "args": { + "External id": 232774,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115734005.272, "dur": 2.730, + "args": { + "External id": 232775,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 2886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115734012.119, "dur": 3.560, + "args": { + "External id": 232776,"Record function id": 0, "Ev Idx": 2887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115734013.127, "dur": 2.157, + "args": { + "External id": 232777,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115734013.599, "dur": 1.301, + "args": { + "External id": 232778,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115734014.040, "dur": 0.748, + "args": { + "External id": 232779,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 2890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115734019.417, "dur": 15083.720, + "args": { + "External id": 232780,"Record function id": 0, "Sequence number": 2757767, "Fwd thread id": 1, "Ev Idx": 2891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115734020.718, "dur": 15074.362, + "args": { + "External id": 232781,"Sequence number": 2757767, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 2892 + } + }, + { + "ph": "f", "id": 189, "pid": 4183440, "tid": 31337, "ts": 667115734020.718, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.11)", "pid": 4183440, "tid": 31337, + "ts": 667115734051.799, "dur": 35.346, + "args": { + "External id": 232782,"Record function id": 0, "Ev Idx": 2893 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.11)", "pid": 4183440, "tid": 31337, + "ts": 667115734094.406, "dur": 63.756, + "args": { + "External id": 232783,"Record function id": 0, "Ev Idx": 2894 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.11)", "pid": 4183440, "tid": 31337, + "ts": 667115734167.617, "dur": 14919.808, + "args": { + "External id": 232784,"Record function id": 0, "Ev Idx": 2895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115734248.110, "dur": 6.704, + "args": { + "External id": 232785,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115734263.783, "dur": 4.485, + "args": { + "External id": 232786,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 2897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115734281.069, "dur": 14105.046, + "args": { + "External id": 232787,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 2898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115734293.534, "dur": 14084.781, + "args": { + "External id": 232788,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 2899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115734310.910, "dur": 13.739, + "args": { + "External id": 232789,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115734328.640, "dur": 14008.776, + "args": { + "External id": 232790,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 2901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115734331.039, "dur": 14005.679, + "args": { + "External id": 232791,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 2902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115734334.853, "dur": 5.039, + "args": { + "External id": 232792,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115734341.644, "dur": 13991.456, + "args": { + "External id": 232793,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 2904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115748471.591, "dur": 9.041, + "args": { + "External id": 232794,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 2905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115748474.659, "dur": 5.554, + "args": { + "External id": 232795,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115748522.772, "dur": 291.679, + "args": { + "External id": 232796,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 2907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115748548.509, "dur": 261.097, + "args": { + "External id": 232797,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2908, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115748560.554, "dur": 243.402, + "args": { + "External id": 232798,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 2909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115748833.262, "dur": 2.401, + "args": { + "External id": 232799,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2910, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115748891.153, "dur": 6.174, + "args": { + "External id": 232800,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115748942.629, "dur": 1.643, + "args": { + "External id": 232801,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115748959.684, "dur": 1.228, + "args": { + "External id": 232802,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115748970.648, "dur": 0.644, + "args": { + "External id": 232803,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115748981.865, "dur": 1.118, + "args": { + "External id": 232804,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115748993.749, "dur": 0.756, + "args": { + "External id": 232805,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749004.055, "dur": 0.850, + "args": { + "External id": 232806,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749014.694, "dur": 1.588, + "args": { + "External id": 232807,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749025.357, "dur": 0.837, + "args": { + "External id": 232808,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115749117.116, "dur": 2579.853, + "args": { + "External id": 232809,"Record function id": 0, "Ev Idx": 2920 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.10)", "pid": 4183440, "tid": 31337, + "ts": 667115749136.271, "dur": 987.164, + "args": { + "External id": 232810,"Record function id": 0, "Ev Idx": 2921 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 4183440, "tid": 31337, + "ts": 667115749152.340, "dur": 280.838, + "args": { + "External id": 232811,"Record function id": 0, "Ev Idx": 2922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115749225.866, "dur": 4.073, + "args": { + "External id": 232812,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 2923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115749233.121, "dur": 0.946, + "args": { + "External id": 232813,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 2924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115749235.704, "dur": 1.022, + "args": { + "External id": 232814,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115749238.414, "dur": 0.607, + "args": { + "External id": 232815,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115749240.578, "dur": 1.253, + "args": { + "External id": 232816,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115749243.639, "dur": 0.934, + "args": { + "External id": 232817,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 2928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115749246.522, "dur": 1.702, + "args": { + "External id": 232818,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 2929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115749250.140, "dur": 3.102, + "args": { + "External id": 232819,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115749254.997, "dur": 0.992, + "args": { + "External id": 232820,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115749257.606, "dur": 0.714, + "args": { + "External id": 232821,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 2932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115749276.307, "dur": 130.609, + "args": { + "External id": 232822,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 2933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115749291.380, "dur": 111.717, + "args": { + "External id": 232823,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 2934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115749303.628, "dur": 13.143, + "args": { + "External id": 232824,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115749319.787, "dur": 57.906, + "args": { + "External id": 232825,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 2936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115749322.297, "dur": 55.035, + "args": { + "External id": 232826,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 2937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749325.972, "dur": 6.063, + "args": { + "External id": 232827,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115749333.710, "dur": 43.152, + "args": { + "External id": 232828,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 2939 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.9", "pid": 4183440, "tid": 31337, + "ts": 667115749526.213, "dur": 590.155, + "args": { + "External id": 232829,"Record function id": 0, "Ev Idx": 2940 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 4183440, "tid": 31337, + "ts": 667115749543.596, "dur": 560.635, + "args": { + "External id": 232830,"Record function id": 0, "Ev Idx": 2941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115749598.188, "dur": 5.509, + "args": { + "External id": 232831,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115749619.460, "dur": 27.455, + "args": { + "External id": 232832,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 2943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749624.139, "dur": 1.563, + "args": { + "External id": 232833,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749627.933, "dur": 0.593, + "args": { + "External id": 232834,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749629.766, "dur": 2.270, + "args": { + "External id": 232835,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749633.469, "dur": 0.570, + "args": { + "External id": 232836,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749635.333, "dur": 0.406, + "args": { + "External id": 232837,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749636.789, "dur": 0.644, + "args": { + "External id": 232838,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749639.403, "dur": 0.283, + "args": { + "External id": 232839,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749640.899, "dur": 0.270, + "args": { + "External id": 232840,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749642.574, "dur": 0.445, + "args": { + "External id": 232841,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115749706.885, "dur": 35.527, + "args": { + "External id": 232842,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 2953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115749778.256, "dur": 104.531, + "args": { + "External id": 232843,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 2954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115749789.830, "dur": 4.683, + "args": { + "External id": 232844,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115749799.833, "dur": 12.100, + "args": { + "External id": 232845,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 2956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115749803.860, "dur": 7.661, + "args": { + "External id": 232846,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 2957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749807.303, "dur": 2.599, + "args": { + "External id": 232847,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 2958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115749819.478, "dur": 23.114, + "args": { + "External id": 232848,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 2959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749821.630, "dur": 0.358, + "args": { + "External id": 232849,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749823.727, "dur": 0.445, + "args": { + "External id": 232850,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749825.558, "dur": 0.563, + "args": { + "External id": 232851,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749827.775, "dur": 0.840, + "args": { + "External id": 232852,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749830.082, "dur": 0.363, + "args": { + "External id": 232853,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749832.065, "dur": 0.311, + "args": { + "External id": 232854,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749833.441, "dur": 0.538, + "args": { + "External id": 232855,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749835.180, "dur": 2.017, + "args": { + "External id": 232856,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115749838.613, "dur": 0.862, + "args": { + "External id": 232857,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 2968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115749855.509, "dur": 20.226, + "args": { + "External id": 232858,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 2969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115749928.238, "dur": 110.028, + "args": { + "External id": 232859,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 2970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115749952.438, "dur": 82.541, + "args": { + "External id": 232860,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2971, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115749961.795, "dur": 69.399, + "args": { + "External id": 232861,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 2972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115750053.767, "dur": 2.041, + "args": { + "External id": 232862,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2973, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115750130.081, "dur": 1510.790, + "args": { + "External id": 232863,"Sequence number": 2757766, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 2974 + } + }, + { + "ph": "f", "id": 190, "pid": 4183440, "tid": 31337, "ts": 667115750130.081, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115750235.853, "dur": 98.652, + "args": { + "External id": 232864,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 2975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115750372.183, "dur": 35.645, + "args": { + "External id": 232865,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 2976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115750425.592, "dur": 39.844, + "args": { + "External id": 232866,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 2977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115750474.490, "dur": 45.129, + "args": { + "External id": 232867,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 2978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115750528.410, "dur": 36.015, + "args": { + "External id": 232868,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 2979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115750571.020, "dur": 19.858, + "args": { + "External id": 232869,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 2980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115750599.170, "dur": 28.173, + "args": { + "External id": 232870,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 2981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115750686.919, "dur": 26.211, + "args": { + "External id": 232871,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 2982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115750735.580, "dur": 25.716, + "args": { + "External id": 232872,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115750781.213, "dur": 18.146, + "args": { + "External id": 232873,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 2984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115750812.189, "dur": 13.529, + "args": { + "External id": 232874,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 2985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115750836.213, "dur": 39.807, + "args": { + "External id": 232875,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115750879.223, "dur": 29.924, + "args": { + "External id": 232876,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115750934.249, "dur": 158.143, + "args": { + "External id": 232877,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115751004.496, "dur": 5.591, + "args": { + "External id": 232878,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115751012.127, "dur": 3.388, + "args": { + "External id": 232879,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115751121.894, "dur": 22.429, + "args": { + "External id": 232880,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115751155.199, "dur": 13.092, + "args": { + "External id": 232881,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115751177.388, "dur": 40.108, + "args": { + "External id": 232882,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115751222.586, "dur": 33.097, + "args": { + "External id": 232883,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115751262.067, "dur": 26.941, + "args": { + "External id": 232884,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115751292.940, "dur": 30.260, + "args": { + "External id": 232885,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115751330.835, "dur": 26.185, + "args": { + "External id": 232886,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 2997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115751362.573, "dur": 27.212, + "args": { + "External id": 232887,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 2998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115751406.102, "dur": 19.328, + "args": { + "External id": 232888,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 2999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115751440.989, "dur": 21.537, + "args": { + "External id": 232889,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115751475.497, "dur": 49.202, + "args": { + "External id": 232890,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 3001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115751560.834, "dur": 19.731, + "args": { + "External id": 232891,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 3002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115751594.861, "dur": 15.342, + "args": { + "External id": 232892,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 3003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115751719.750, "dur": 15.766, + "args": { + "External id": 232893,"Record function id": 0, "Ev Idx": 3004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115751722.973, "dur": 11.661, + "args": { + "External id": 232894,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115751727.313, "dur": 6.057, + "args": { + "External id": 232895,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115751728.825, "dur": 4.447, + "args": { + "External id": 232896,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115751739.429, "dur": 4.786, + "args": { + "External id": 232897,"Record function id": 0, "Ev Idx": 3008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115751740.984, "dur": 2.754, + "args": { + "External id": 232898,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115751741.969, "dur": 1.317, + "args": { + "External id": 232899,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115751742.452, "dur": 0.756, + "args": { + "External id": 232900,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115751747.548, "dur": 7.106, + "args": { + "External id": 232901,"Record function id": 0, "Ev Idx": 3012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115751748.542, "dur": 2.505, + "args": { + "External id": 232902,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115751749.222, "dur": 1.384, + "args": { + "External id": 232903,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115751749.724, "dur": 0.768, + "args": { + "External id": 232904,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115751757.802, "dur": 3.563, + "args": { + "External id": 232905,"Record function id": 0, "Ev Idx": 3016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115751758.887, "dur": 2.076, + "args": { + "External id": 232906,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115751759.402, "dur": 1.142, + "args": { + "External id": 232907,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115751759.792, "dur": 0.643, + "args": { + "External id": 232908,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115751764.849, "dur": 3.810, + "args": { + "External id": 232909,"Record function id": 0, "Ev Idx": 3020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115751765.888, "dur": 2.330, + "args": { + "External id": 232910,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115751766.392, "dur": 1.395, + "args": { + "External id": 232911,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115751767.109, "dur": 0.572, + "args": { + "External id": 232912,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115751771.798, "dur": 3.902, + "args": { + "External id": 232913,"Record function id": 0, "Ev Idx": 3024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115751772.794, "dur": 2.486, + "args": { + "External id": 232914,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115751773.397, "dur": 1.471, + "args": { + "External id": 232915,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115751774.223, "dur": 0.565, + "args": { + "External id": 232916,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115751779.000, "dur": 5.555, + "args": { + "External id": 232917,"Record function id": 0, "Ev Idx": 3028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115751779.982, "dur": 4.141, + "args": { + "External id": 232918,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115751780.563, "dur": 3.141, + "args": { + "External id": 232919,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115751781.242, "dur": 2.381, + "args": { + "External id": 232920,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115751787.721, "dur": 4.079, + "args": { + "External id": 232921,"Record function id": 0, "Ev Idx": 3032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115751788.776, "dur": 2.605, + "args": { + "External id": 232922,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115751789.255, "dur": 1.723, + "args": { + "External id": 232923,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115751790.040, "dur": 0.860, + "args": { + "External id": 232924,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115751794.926, "dur": 3.895, + "args": { + "External id": 232925,"Record function id": 0, "Ev Idx": 3036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115751796.121, "dur": 2.249, + "args": { + "External id": 232926,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115751796.607, "dur": 1.348, + "args": { + "External id": 232927,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115751797.251, "dur": 0.625, + "args": { + "External id": 232928,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115751802.318, "dur": 15091.929, + "args": { + "External id": 232929,"Record function id": 0, "Sequence number": 2757765, "Fwd thread id": 1, "Ev Idx": 3040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115751803.528, "dur": 15082.628, + "args": { + "External id": 232930,"Sequence number": 2757765, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 3041 + } + }, + { + "ph": "f", "id": 191, "pid": 4183440, "tid": 31337, "ts": 667115751803.528, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.10)", "pid": 4183440, "tid": 31337, + "ts": 667115751836.152, "dur": 42.964, + "args": { + "External id": 232931,"Record function id": 0, "Ev Idx": 3042 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.10)", "pid": 4183440, "tid": 31337, + "ts": 667115751887.250, "dur": 64.962, + "args": { + "External id": 232932,"Record function id": 0, "Ev Idx": 3043 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.10)", "pid": 4183440, "tid": 31337, + "ts": 667115751958.818, "dur": 14919.549, + "args": { + "External id": 232933,"Record function id": 0, "Ev Idx": 3044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115752048.426, "dur": 6.481, + "args": { + "External id": 232934,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115752063.969, "dur": 5.087, + "args": { + "External id": 232935,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 3046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115752082.575, "dur": 14051.401, + "args": { + "External id": 232936,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 3047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115752103.422, "dur": 14022.741, + "args": { + "External id": 232937,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 3048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115752125.040, "dur": 13.469, + "args": { + "External id": 232938,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115752142.678, "dur": 13950.220, + "args": { + "External id": 232939,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 3050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115752145.249, "dur": 13946.830, + "args": { + "External id": 232940,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 3051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115752149.058, "dur": 5.146, + "args": { + "External id": 232941,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115752156.051, "dur": 13932.426, + "args": { + "External id": 232942,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 3053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115766221.626, "dur": 9.830, + "args": { + "External id": 232943,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 3054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115766225.215, "dur": 5.857, + "args": { + "External id": 232944,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115766257.525, "dur": 310.690, + "args": { + "External id": 232945,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 3056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115766282.824, "dur": 280.502, + "args": { + "External id": 232946,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3057, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115766293.870, "dur": 263.894, + "args": { + "External id": 232947,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 3058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115766587.236, "dur": 2.318, + "args": { + "External id": 232948,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3059, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115766644.990, "dur": 38.261, + "args": { + "External id": 232949,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115766730.057, "dur": 1.851, + "args": { + "External id": 232950,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115766746.250, "dur": 1.272, + "args": { + "External id": 232951,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115766758.489, "dur": 1.012, + "args": { + "External id": 232952,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115766770.851, "dur": 2.714, + "args": { + "External id": 232953,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115766782.720, "dur": 0.778, + "args": { + "External id": 232954,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115766793.003, "dur": 1.052, + "args": { + "External id": 232955,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115766804.565, "dur": 1.799, + "args": { + "External id": 232956,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115766815.899, "dur": 2.208, + "args": { + "External id": 232957,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115766909.051, "dur": 2518.222, + "args": { + "External id": 232958,"Record function id": 0, "Ev Idx": 3069 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.9)", "pid": 4183440, "tid": 31337, + "ts": 667115766927.622, "dur": 982.806, + "args": { + "External id": 232959,"Record function id": 0, "Ev Idx": 3070 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 4183440, "tid": 31337, + "ts": 667115766944.084, "dur": 297.875, + "args": { + "External id": 232960,"Record function id": 0, "Ev Idx": 3071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115767033.632, "dur": 3.910, + "args": { + "External id": 232961,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 3072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115767040.767, "dur": 0.929, + "args": { + "External id": 232962,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 3073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115767043.411, "dur": 0.659, + "args": { + "External id": 232963,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115767045.462, "dur": 0.738, + "args": { + "External id": 232964,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115767047.475, "dur": 0.717, + "args": { + "External id": 232965,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115767049.499, "dur": 0.635, + "args": { + "External id": 232966,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115767051.648, "dur": 2.955, + "args": { + "External id": 232967,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 3078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115767056.086, "dur": 0.704, + "args": { + "External id": 232968,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115767058.271, "dur": 0.567, + "args": { + "External id": 232969,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115767060.223, "dur": 0.509, + "args": { + "External id": 232970,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115767078.888, "dur": 135.310, + "args": { + "External id": 232971,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 3082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115767094.632, "dur": 115.731, + "args": { + "External id": 232972,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 3083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115767107.028, "dur": 13.206, + "args": { + "External id": 232973,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115767123.188, "dur": 60.960, + "args": { + "External id": 232974,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 3085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115767125.412, "dur": 58.375, + "args": { + "External id": 232975,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 3086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767128.979, "dur": 6.332, + "args": { + "External id": 232976,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115767136.990, "dur": 46.205, + "args": { + "External id": 232977,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 3088 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.8", "pid": 4183440, "tid": 31337, + "ts": 667115767314.833, "dur": 587.370, + "args": { + "External id": 232978,"Record function id": 0, "Ev Idx": 3089 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 4183440, "tid": 31337, + "ts": 667115767331.328, "dur": 558.040, + "args": { + "External id": 232979,"Record function id": 0, "Ev Idx": 3090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115767383.525, "dur": 4.746, + "args": { + "External id": 232980,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115767403.912, "dur": 25.212, + "args": { + "External id": 232981,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 3092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767407.919, "dur": 1.438, + "args": { + "External id": 232982,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767411.148, "dur": 2.350, + "args": { + "External id": 232983,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767414.559, "dur": 0.440, + "args": { + "External id": 232984,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767416.801, "dur": 0.415, + "args": { + "External id": 232985,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767418.774, "dur": 0.260, + "args": { + "External id": 232986,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767419.913, "dur": 0.764, + "args": { + "External id": 232987,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767421.890, "dur": 0.426, + "args": { + "External id": 232988,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767423.434, "dur": 0.480, + "args": { + "External id": 232989,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767425.089, "dur": 0.303, + "args": { + "External id": 232990,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115767438.025, "dur": 28.815, + "args": { + "External id": 232991,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 3102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115767513.193, "dur": 102.280, + "args": { + "External id": 232992,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 3103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115767523.795, "dur": 6.486, + "args": { + "External id": 232993,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115767535.318, "dur": 10.017, + "args": { + "External id": 232994,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 3105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115767539.275, "dur": 5.650, + "args": { + "External id": 232995,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 3106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767542.809, "dur": 0.667, + "args": { + "External id": 232996,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 3107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115767552.160, "dur": 22.660, + "args": { + "External id": 232997,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 3108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767554.003, "dur": 0.547, + "args": { + "External id": 232998,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767555.984, "dur": 0.493, + "args": { + "External id": 232999,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767557.413, "dur": 0.683, + "args": { + "External id": 233000,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767559.901, "dur": 0.561, + "args": { + "External id": 233001,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767562.127, "dur": 0.333, + "args": { + "External id": 233002,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767564.068, "dur": 0.558, + "args": { + "External id": 233003,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767565.571, "dur": 1.951, + "args": { + "External id": 233004,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767569.026, "dur": 0.341, + "args": { + "External id": 233005,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115767570.837, "dur": 0.501, + "args": { + "External id": 233006,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115767586.455, "dur": 21.950, + "args": { + "External id": 233007,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 3118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115767696.650, "dur": 121.964, + "args": { + "External id": 233008,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 3119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115767720.476, "dur": 94.660, + "args": { + "External id": 233009,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3120, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115767731.566, "dur": 79.560, + "args": { + "External id": 233010,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 3121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115767834.111, "dur": 1.808, + "args": { + "External id": 233011,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3122, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115767918.120, "dur": 1488.855, + "args": { + "External id": 233012,"Sequence number": 2757764, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 3123 + } + }, + { + "ph": "f", "id": 192, "pid": 4183440, "tid": 31337, "ts": 667115767918.120, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115768025.876, "dur": 98.795, + "args": { + "External id": 233013,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 3124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115768162.247, "dur": 35.541, + "args": { + "External id": 233014,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 3125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115768215.265, "dur": 38.667, + "args": { + "External id": 233015,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 3126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115768262.987, "dur": 24.124, + "args": { + "External id": 233016,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 3127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115768293.220, "dur": 31.765, + "args": { + "External id": 233017,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 3128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115768333.352, "dur": 19.626, + "args": { + "External id": 233018,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 3129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115768359.544, "dur": 27.033, + "args": { + "External id": 233019,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 3130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115768408.065, "dur": 20.166, + "args": { + "External id": 233020,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 3131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115768445.062, "dur": 25.808, + "args": { + "External id": 233021,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115768487.666, "dur": 39.147, + "args": { + "External id": 233022,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 3133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115768542.245, "dur": 13.435, + "args": { + "External id": 233023,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 3134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115768564.904, "dur": 38.745, + "args": { + "External id": 233024,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115768607.501, "dur": 30.371, + "args": { + "External id": 233025,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115768698.651, "dur": 168.907, + "args": { + "External id": 233026,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115768773.549, "dur": 6.524, + "args": { + "External id": 233027,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115768782.277, "dur": 4.390, + "args": { + "External id": 233028,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115768900.915, "dur": 25.633, + "args": { + "External id": 233029,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115768939.423, "dur": 15.547, + "args": { + "External id": 233030,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115768962.956, "dur": 50.641, + "args": { + "External id": 233031,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115769018.734, "dur": 32.621, + "args": { + "External id": 233032,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115769057.591, "dur": 26.629, + "args": { + "External id": 233033,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115769090.735, "dur": 28.393, + "args": { + "External id": 233034,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115769124.422, "dur": 25.484, + "args": { + "External id": 233035,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115769155.555, "dur": 30.457, + "args": { + "External id": 233036,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115769202.251, "dur": 20.595, + "args": { + "External id": 233037,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 3148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115769241.899, "dur": 23.991, + "args": { + "External id": 233038,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115769278.042, "dur": 15.930, + "args": { + "External id": 233039,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 3150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115769307.041, "dur": 31.942, + "args": { + "External id": 233040,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 3151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115769360.190, "dur": 15.481, + "args": { + "External id": 233041,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 3152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115769452.119, "dur": 14.563, + "args": { + "External id": 233042,"Record function id": 0, "Ev Idx": 3153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115769455.253, "dur": 10.546, + "args": { + "External id": 233043,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115769459.345, "dur": 5.546, + "args": { + "External id": 233044,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115769460.957, "dur": 3.849, + "args": { + "External id": 233045,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115769470.447, "dur": 4.337, + "args": { + "External id": 233046,"Record function id": 0, "Ev Idx": 3157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115769471.731, "dur": 2.563, + "args": { + "External id": 233047,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115769472.447, "dur": 1.387, + "args": { + "External id": 233048,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115769472.868, "dur": 0.893, + "args": { + "External id": 233049,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115769478.142, "dur": 4.040, + "args": { + "External id": 233050,"Record function id": 0, "Ev Idx": 3161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115769479.482, "dur": 2.251, + "args": { + "External id": 233051,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115769480.037, "dur": 1.266, + "args": { + "External id": 233052,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115769480.606, "dur": 0.605, + "args": { + "External id": 233053,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115769485.377, "dur": 5.815, + "args": { + "External id": 233054,"Record function id": 0, "Ev Idx": 3165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115769486.531, "dur": 4.202, + "args": { + "External id": 233055,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115769487.042, "dur": 3.292, + "args": { + "External id": 233056,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115769487.506, "dur": 2.726, + "args": { + "External id": 233057,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115769517.638, "dur": 6.475, + "args": { + "External id": 233058,"Record function id": 0, "Ev Idx": 3169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115769519.352, "dur": 4.080, + "args": { + "External id": 233059,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115769520.388, "dur": 2.246, + "args": { + "External id": 233060,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115769521.063, "dur": 1.408, + "args": { + "External id": 233061,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115769527.307, "dur": 4.384, + "args": { + "External id": 233062,"Record function id": 0, "Ev Idx": 3173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115769528.700, "dur": 2.553, + "args": { + "External id": 233063,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115769529.169, "dur": 1.691, + "args": { + "External id": 233064,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115769529.975, "dur": 0.811, + "args": { + "External id": 233065,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115769534.897, "dur": 4.042, + "args": { + "External id": 233066,"Record function id": 0, "Ev Idx": 3177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115769536.195, "dur": 2.308, + "args": { + "External id": 233067,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115769536.736, "dur": 1.380, + "args": { + "External id": 233068,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115769537.514, "dur": 0.507, + "args": { + "External id": 233069,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115769542.017, "dur": 4.391, + "args": { + "External id": 233070,"Record function id": 0, "Ev Idx": 3181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115769543.599, "dur": 2.353, + "args": { + "External id": 233071,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115769544.360, "dur": 1.206, + "args": { + "External id": 233072,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115769544.814, "dur": 0.639, + "args": { + "External id": 233073,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115769549.475, "dur": 3.515, + "args": { + "External id": 233074,"Record function id": 0, "Ev Idx": 3185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115769550.568, "dur": 1.972, + "args": { + "External id": 233075,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115769551.076, "dur": 1.076, + "args": { + "External id": 233076,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115769551.405, "dur": 0.646, + "args": { + "External id": 233077,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115769556.586, "dur": 15010.212, + "args": { + "External id": 233078,"Record function id": 0, "Sequence number": 2757763, "Fwd thread id": 1, "Ev Idx": 3189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115769557.794, "dur": 14999.414, + "args": { + "External id": 233079,"Sequence number": 2757763, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 3190 + } + }, + { + "ph": "f", "id": 193, "pid": 4183440, "tid": 31337, "ts": 667115769557.794, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.9)", "pid": 4183440, "tid": 31337, + "ts": 667115769586.501, "dur": 36.166, + "args": { + "External id": 233080,"Record function id": 0, "Ev Idx": 3191 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.9)", "pid": 4183440, "tid": 31337, + "ts": 667115769629.830, "dur": 99.504, + "args": { + "External id": 233081,"Record function id": 0, "Ev Idx": 3192 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.9)", "pid": 4183440, "tid": 31337, + "ts": 667115769737.136, "dur": 14812.062, + "args": { + "External id": 233082,"Record function id": 0, "Ev Idx": 3193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115769830.579, "dur": 7.611, + "args": { + "External id": 233083,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115769850.993, "dur": 5.483, + "args": { + "External id": 233084,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 3195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115769870.782, "dur": 14036.283, + "args": { + "External id": 233085,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 3196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115769884.279, "dur": 14014.740, + "args": { + "External id": 233086,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 3197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115769907.784, "dur": 15.500, + "args": { + "External id": 233087,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115769927.671, "dur": 13938.380, + "args": { + "External id": 233088,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 3199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115769930.294, "dur": 13934.943, + "args": { + "External id": 233089,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 3200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115769934.422, "dur": 5.195, + "args": { + "External id": 233090,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115769941.434, "dur": 13920.041, + "args": { + "External id": 233091,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 3202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115783991.918, "dur": 8.513, + "args": { + "External id": 233092,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 3203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115783994.754, "dur": 5.338, + "args": { + "External id": 233093,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115784026.457, "dur": 253.335, + "args": { + "External id": 233094,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 3205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115784050.896, "dur": 224.527, + "args": { + "External id": 233095,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3206, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115784061.383, "dur": 209.397, + "args": { + "External id": 233096,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 3207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115784293.988, "dur": 1.983, + "args": { + "External id": 233097,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3208, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115784343.880, "dur": 5.470, + "args": { + "External id": 233098,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115784390.523, "dur": 1.489, + "args": { + "External id": 233099,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115784406.210, "dur": 1.096, + "args": { + "External id": 233100,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115784419.858, "dur": 0.761, + "args": { + "External id": 233101,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115784430.779, "dur": 0.721, + "args": { + "External id": 233102,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115784440.358, "dur": 0.727, + "args": { + "External id": 233103,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115784450.480, "dur": 1.038, + "args": { + "External id": 233104,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115784463.554, "dur": 1.862, + "args": { + "External id": 233105,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115784474.129, "dur": 0.902, + "args": { + "External id": 233106,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115784582.153, "dur": 2474.693, + "args": { + "External id": 233107,"Record function id": 0, "Ev Idx": 3218 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.8)", "pid": 4183440, "tid": 31337, + "ts": 667115784600.487, "dur": 921.580, + "args": { + "External id": 233108,"Record function id": 0, "Ev Idx": 3219 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 4183440, "tid": 31337, + "ts": 667115784614.447, "dur": 320.170, + "args": { + "External id": 233109,"Record function id": 0, "Ev Idx": 3220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115784723.414, "dur": 4.830, + "args": { + "External id": 233110,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 3221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115784731.535, "dur": 0.845, + "args": { + "External id": 233111,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 3222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115784734.133, "dur": 0.846, + "args": { + "External id": 233112,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115784736.629, "dur": 3.045, + "args": { + "External id": 233113,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115784741.062, "dur": 0.903, + "args": { + "External id": 233114,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115784743.325, "dur": 0.891, + "args": { + "External id": 233115,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115784745.661, "dur": 1.494, + "args": { + "External id": 233116,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 3227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115784748.279, "dur": 0.696, + "args": { + "External id": 233117,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115784750.408, "dur": 0.621, + "args": { + "External id": 233118,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115784752.363, "dur": 0.705, + "args": { + "External id": 233119,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115784771.595, "dur": 135.331, + "args": { + "External id": 233120,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 3231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115784787.233, "dur": 115.995, + "args": { + "External id": 233121,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 3232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115784799.387, "dur": 13.002, + "args": { + "External id": 233122,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115784815.174, "dur": 62.993, + "args": { + "External id": 233123,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 3234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115784817.732, "dur": 60.104, + "args": { + "External id": 233124,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 3235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115784821.772, "dur": 7.194, + "args": { + "External id": 233125,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115784830.887, "dur": 46.294, + "args": { + "External id": 233126,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 3237 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.7", "pid": 4183440, "tid": 31337, + "ts": 667115785011.098, "dur": 498.941, + "args": { + "External id": 233127,"Record function id": 0, "Ev Idx": 3238 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 4183440, "tid": 31337, + "ts": 667115785026.108, "dur": 453.073, + "args": { + "External id": 233128,"Record function id": 0, "Ev Idx": 3239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115785079.493, "dur": 4.644, + "args": { + "External id": 233129,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115785099.735, "dur": 24.124, + "args": { + "External id": 233130,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 3241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785104.030, "dur": 1.547, + "args": { + "External id": 233131,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785107.609, "dur": 0.571, + "args": { + "External id": 233132,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785109.342, "dur": 0.410, + "args": { + "External id": 233133,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785110.806, "dur": 0.619, + "args": { + "External id": 233134,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785112.319, "dur": 0.523, + "args": { + "External id": 233135,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785113.822, "dur": 0.655, + "args": { + "External id": 233136,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785115.576, "dur": 2.409, + "args": { + "External id": 233137,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785118.842, "dur": 0.424, + "args": { + "External id": 233138,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785120.063, "dur": 0.376, + "args": { + "External id": 233139,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115785133.206, "dur": 29.831, + "args": { + "External id": 233140,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 3251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115785190.917, "dur": 82.967, + "args": { + "External id": 233141,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 3252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115785199.873, "dur": 2.970, + "args": { + "External id": 233142,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115785207.335, "dur": 9.330, + "args": { + "External id": 233143,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 3254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115785211.489, "dur": 4.753, + "args": { + "External id": 233144,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 3255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785214.581, "dur": 0.595, + "args": { + "External id": 233145,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 3256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115785222.321, "dur": 17.341, + "args": { + "External id": 233146,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 3257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785224.141, "dur": 0.302, + "args": { + "External id": 233147,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785225.545, "dur": 0.544, + "args": { + "External id": 233148,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785227.037, "dur": 0.353, + "args": { + "External id": 233149,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785228.512, "dur": 2.020, + "args": { + "External id": 233150,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785231.391, "dur": 0.379, + "args": { + "External id": 233151,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785232.638, "dur": 0.398, + "args": { + "External id": 233152,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785233.868, "dur": 0.429, + "args": { + "External id": 233153,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785235.239, "dur": 0.273, + "args": { + "External id": 233154,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115785236.434, "dur": 0.364, + "args": { + "External id": 233155,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115785248.162, "dur": 18.716, + "args": { + "External id": 233156,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 3267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115785315.960, "dur": 103.685, + "args": { + "External id": 233157,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 3268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115785336.418, "dur": 79.837, + "args": { + "External id": 233158,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3269, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115785345.562, "dur": 66.983, + "args": { + "External id": 233159,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 3270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115785432.568, "dur": 1.909, + "args": { + "External id": 233160,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3271, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115785529.985, "dur": 1502.731, + "args": { + "External id": 233161,"Sequence number": 2757762, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 3272 + } + }, + { + "ph": "f", "id": 194, "pid": 4183440, "tid": 31337, "ts": 667115785529.985, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115785639.205, "dur": 138.010, + "args": { + "External id": 233162,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 3273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115785823.259, "dur": 36.139, + "args": { + "External id": 233163,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 3274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115785876.306, "dur": 39.481, + "args": { + "External id": 233164,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 3275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115785924.367, "dur": 25.114, + "args": { + "External id": 233165,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 3276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115785956.572, "dur": 32.280, + "args": { + "External id": 233166,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 3277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115785997.029, "dur": 20.867, + "args": { + "External id": 233167,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 3278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115786023.762, "dur": 27.544, + "args": { + "External id": 233168,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 3279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115786073.202, "dur": 19.968, + "args": { + "External id": 233169,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 3280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115786111.709, "dur": 26.721, + "args": { + "External id": 233170,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115786153.786, "dur": 17.247, + "args": { + "External id": 233171,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 3282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115786182.594, "dur": 13.876, + "args": { + "External id": 233172,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 3283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115786203.626, "dur": 32.948, + "args": { + "External id": 233173,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115786240.006, "dur": 28.853, + "args": { + "External id": 233174,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115786294.031, "dur": 155.727, + "args": { + "External id": 233175,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115786364.678, "dur": 5.698, + "args": { + "External id": 233176,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115786372.093, "dur": 2.713, + "args": { + "External id": 233177,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115786476.642, "dur": 40.532, + "args": { + "External id": 233178,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115786530.879, "dur": 14.345, + "args": { + "External id": 233179,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115786554.079, "dur": 44.882, + "args": { + "External id": 233180,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115786605.529, "dur": 29.748, + "args": { + "External id": 233181,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115786644.311, "dur": 77.934, + "args": { + "External id": 233182,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115786729.865, "dur": 29.428, + "args": { + "External id": 233183,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115786766.196, "dur": 26.099, + "args": { + "External id": 233184,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115786798.582, "dur": 26.949, + "args": { + "External id": 233185,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115786844.554, "dur": 22.134, + "args": { + "External id": 233186,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 3297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115786883.005, "dur": 24.562, + "args": { + "External id": 233187,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115786920.226, "dur": 17.420, + "args": { + "External id": 233188,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 3299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115786953.270, "dur": 15.484, + "args": { + "External id": 233189,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 3300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115786980.931, "dur": 15.496, + "args": { + "External id": 233190,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 3301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115787079.920, "dur": 14.611, + "args": { + "External id": 233191,"Record function id": 0, "Ev Idx": 3302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115787083.155, "dur": 10.280, + "args": { + "External id": 233192,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115787087.378, "dur": 5.257, + "args": { + "External id": 233193,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115787088.718, "dur": 3.789, + "args": { + "External id": 233194,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115787098.173, "dur": 4.114, + "args": { + "External id": 233195,"Record function id": 0, "Ev Idx": 3306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115787099.335, "dur": 2.483, + "args": { + "External id": 233196,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115787100.085, "dur": 1.250, + "args": { + "External id": 233197,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115787100.472, "dur": 0.795, + "args": { + "External id": 233198,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115787105.488, "dur": 4.553, + "args": { + "External id": 233199,"Record function id": 0, "Ev Idx": 3310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115787106.737, "dur": 2.877, + "args": { + "External id": 233200,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115787107.429, "dur": 1.784, + "args": { + "External id": 233201,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115787108.161, "dur": 0.970, + "args": { + "External id": 233202,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115787113.083, "dur": 5.207, + "args": { + "External id": 233203,"Record function id": 0, "Ev Idx": 3314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115787114.049, "dur": 3.793, + "args": { + "External id": 233204,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115787114.549, "dur": 2.866, + "args": { + "External id": 233205,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115787115.071, "dur": 2.255, + "args": { + "External id": 233206,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115787121.233, "dur": 3.961, + "args": { + "External id": 233207,"Record function id": 0, "Ev Idx": 3318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115787122.295, "dur": 2.463, + "args": { + "External id": 233208,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115787122.799, "dur": 1.539, + "args": { + "External id": 233209,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115787123.266, "dur": 0.983, + "args": { + "External id": 233210,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115787128.195, "dur": 4.080, + "args": { + "External id": 233211,"Record function id": 0, "Ev Idx": 3322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115787129.469, "dur": 2.364, + "args": { + "External id": 233212,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115787130.233, "dur": 1.208, + "args": { + "External id": 233213,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115787130.766, "dur": 0.600, + "args": { + "External id": 233214,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115787135.385, "dur": 7.253, + "args": { + "External id": 233215,"Record function id": 0, "Ev Idx": 3326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115787136.705, "dur": 5.494, + "args": { + "External id": 233216,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115787137.419, "dur": 4.379, + "args": { + "External id": 233217,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115787137.851, "dur": 3.847, + "args": { + "External id": 233218,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115787145.579, "dur": 3.529, + "args": { + "External id": 233219,"Record function id": 0, "Ev Idx": 3330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115787146.674, "dur": 2.018, + "args": { + "External id": 233220,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115787147.141, "dur": 1.140, + "args": { + "External id": 233221,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115787147.618, "dur": 0.564, + "args": { + "External id": 233222,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115787152.038, "dur": 3.434, + "args": { + "External id": 233223,"Record function id": 0, "Ev Idx": 3334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115787153.118, "dur": 1.937, + "args": { + "External id": 233224,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115787153.612, "dur": 1.052, + "args": { + "External id": 233225,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115787154.019, "dur": 0.546, + "args": { + "External id": 233226,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115787159.061, "dur": 16943.505, + "args": { + "External id": 233227,"Record function id": 0, "Sequence number": 2757761, "Fwd thread id": 1, "Ev Idx": 3338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115787160.219, "dur": 16934.115, + "args": { + "External id": 233228,"Sequence number": 2757761, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 3339 + } + }, + { + "ph": "f", "id": 195, "pid": 4183440, "tid": 31337, "ts": 667115787160.219, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.8)", "pid": 4183440, "tid": 31337, + "ts": 667115787188.984, "dur": 40.864, + "args": { + "External id": 233229,"Record function id": 0, "Ev Idx": 3340 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.8)", "pid": 4183440, "tid": 31337, + "ts": 667115787236.833, "dur": 64.275, + "args": { + "External id": 233230,"Record function id": 0, "Ev Idx": 3341 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.8)", "pid": 4183440, "tid": 31337, + "ts": 667115787306.845, "dur": 16780.542, + "args": { + "External id": 233231,"Record function id": 0, "Ev Idx": 3342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115787397.641, "dur": 6.366, + "args": { + "External id": 233232,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115787413.108, "dur": 4.365, + "args": { + "External id": 233233,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 3344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115787434.565, "dur": 15915.725, + "args": { + "External id": 233234,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 3345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115787447.191, "dur": 15895.176, + "args": { + "External id": 233235,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 3346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115787471.696, "dur": 15.175, + "args": { + "External id": 233236,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115787512.482, "dur": 15794.478, + "args": { + "External id": 233237,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 3348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115787514.924, "dur": 15791.374, + "args": { + "External id": 233238,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 3349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115787519.251, "dur": 5.772, + "args": { + "External id": 233239,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115787527.172, "dur": 15775.495, + "args": { + "External id": 233240,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 3351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115803435.293, "dur": 8.591, + "args": { + "External id": 233241,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 3352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115803437.932, "dur": 5.614, + "args": { + "External id": 233242,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115803468.980, "dur": 346.797, + "args": { + "External id": 233243,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 3354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115803506.369, "dur": 304.313, + "args": { + "External id": 233244,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3355, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115803518.292, "dur": 286.041, + "args": { + "External id": 233245,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 3356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115803835.066, "dur": 2.374, + "args": { + "External id": 233246,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3357, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115803894.537, "dur": 6.343, + "args": { + "External id": 233247,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115803944.643, "dur": 1.305, + "args": { + "External id": 233248,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115803960.189, "dur": 1.463, + "args": { + "External id": 233249,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115803973.825, "dur": 0.940, + "args": { + "External id": 233250,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115803984.218, "dur": 0.634, + "args": { + "External id": 233251,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115803993.563, "dur": 0.690, + "args": { + "External id": 233252,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804004.683, "dur": 0.673, + "args": { + "External id": 233253,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804016.708, "dur": 1.690, + "args": { + "External id": 233254,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804028.076, "dur": 0.833, + "args": { + "External id": 233255,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115804116.290, "dur": 2468.115, + "args": { + "External id": 233256,"Record function id": 0, "Ev Idx": 3367 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.7)", "pid": 4183440, "tid": 31337, + "ts": 667115804134.553, "dur": 943.948, + "args": { + "External id": 233257,"Record function id": 0, "Ev Idx": 3368 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 4183440, "tid": 31337, + "ts": 667115804148.942, "dur": 278.223, + "args": { + "External id": 233258,"Record function id": 0, "Ev Idx": 3369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115804221.272, "dur": 4.125, + "args": { + "External id": 233259,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 3370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115804228.499, "dur": 1.161, + "args": { + "External id": 233260,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 3371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115804231.349, "dur": 0.652, + "args": { + "External id": 233261,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115804233.690, "dur": 2.213, + "args": { + "External id": 233262,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115804237.644, "dur": 0.824, + "args": { + "External id": 233263,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115804240.436, "dur": 0.760, + "args": { + "External id": 233264,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115804242.986, "dur": 1.544, + "args": { + "External id": 233265,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 3376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115804245.976, "dur": 1.019, + "args": { + "External id": 233266,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115804248.590, "dur": 0.679, + "args": { + "External id": 233267,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115804250.752, "dur": 0.849, + "args": { + "External id": 233268,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115804268.952, "dur": 132.209, + "args": { + "External id": 233269,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 3380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115804284.236, "dur": 113.128, + "args": { + "External id": 233270,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 3381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115804295.979, "dur": 12.943, + "args": { + "External id": 233271,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115804311.732, "dur": 59.559, + "args": { + "External id": 233272,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 3383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115804314.048, "dur": 56.959, + "args": { + "External id": 233273,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 3384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804318.078, "dur": 7.289, + "args": { + "External id": 233274,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115804327.057, "dur": 43.250, + "args": { + "External id": 233275,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 3386 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.6", "pid": 4183440, "tid": 31337, + "ts": 667115804517.049, "dur": 554.191, + "args": { + "External id": 233276,"Record function id": 0, "Ev Idx": 3387 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 4183440, "tid": 31337, + "ts": 667115804534.155, "dur": 525.135, + "args": { + "External id": 233277,"Record function id": 0, "Ev Idx": 3388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115804589.826, "dur": 5.854, + "args": { + "External id": 233278,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115804611.958, "dur": 27.174, + "args": { + "External id": 233279,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 3390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804616.302, "dur": 1.522, + "args": { + "External id": 233280,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804619.818, "dur": 0.389, + "args": { + "External id": 233281,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804621.454, "dur": 0.765, + "args": { + "External id": 233282,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804623.540, "dur": 0.618, + "args": { + "External id": 233283,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804624.982, "dur": 0.902, + "args": { + "External id": 233284,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804627.297, "dur": 0.458, + "args": { + "External id": 233285,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804629.194, "dur": 2.275, + "args": { + "External id": 233286,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804632.659, "dur": 0.351, + "args": { + "External id": 233287,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804634.637, "dur": 0.488, + "args": { + "External id": 233288,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115804648.683, "dur": 67.640, + "args": { + "External id": 233289,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 3400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115804751.753, "dur": 95.517, + "args": { + "External id": 233290,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 3401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115804761.767, "dur": 4.184, + "args": { + "External id": 233291,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115804770.590, "dur": 10.010, + "args": { + "External id": 233292,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 3403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115804774.743, "dur": 5.473, + "args": { + "External id": 233293,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 3404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804777.991, "dur": 0.739, + "args": { + "External id": 233294,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 3405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115804787.589, "dur": 23.014, + "args": { + "External id": 233295,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 3406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804789.471, "dur": 0.553, + "args": { + "External id": 233296,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804791.399, "dur": 0.423, + "args": { + "External id": 233297,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804793.657, "dur": 0.645, + "args": { + "External id": 233298,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804795.830, "dur": 2.234, + "args": { + "External id": 233299,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804799.343, "dur": 0.651, + "args": { + "External id": 233300,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804801.287, "dur": 0.500, + "args": { + "External id": 233301,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804803.421, "dur": 0.381, + "args": { + "External id": 233302,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804805.026, "dur": 0.271, + "args": { + "External id": 233303,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115804807.136, "dur": 0.573, + "args": { + "External id": 233304,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115804820.800, "dur": 19.530, + "args": { + "External id": 233305,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 3416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115804889.896, "dur": 109.040, + "args": { + "External id": 233306,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 3417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115804912.858, "dur": 82.621, + "args": { + "External id": 233307,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3418, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115804922.669, "dur": 68.885, + "args": { + "External id": 233308,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 3419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115805011.737, "dur": 1.715, + "args": { + "External id": 233309,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3420, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115805085.085, "dur": 1479.451, + "args": { + "External id": 233310,"Sequence number": 2757760, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 3421 + } + }, + { + "ph": "f", "id": 196, "pid": 4183440, "tid": 31337, "ts": 667115805085.085, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115805189.789, "dur": 101.851, + "args": { + "External id": 233311,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 3422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115805331.539, "dur": 35.732, + "args": { + "External id": 233312,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 3423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115805382.594, "dur": 40.502, + "args": { + "External id": 233313,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 3424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115805431.952, "dur": 26.133, + "args": { + "External id": 233314,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 3425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115805465.792, "dur": 53.809, + "args": { + "External id": 233315,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 3426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115805528.842, "dur": 24.626, + "args": { + "External id": 233316,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 3427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115805560.171, "dur": 28.551, + "args": { + "External id": 233317,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 3428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115805613.469, "dur": 24.484, + "args": { + "External id": 233318,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 3429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115805692.177, "dur": 32.856, + "args": { + "External id": 233319,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115805746.966, "dur": 19.679, + "args": { + "External id": 233320,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 3431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115805779.617, "dur": 16.508, + "args": { + "External id": 233321,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 3432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115805806.281, "dur": 43.497, + "args": { + "External id": 233322,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115805853.174, "dur": 31.062, + "args": { + "External id": 233323,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115805910.438, "dur": 164.284, + "args": { + "External id": 233324,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115805985.259, "dur": 5.612, + "args": { + "External id": 233325,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115805992.573, "dur": 3.340, + "args": { + "External id": 233326,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115806102.391, "dur": 24.688, + "args": { + "External id": 233327,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115806137.632, "dur": 14.148, + "args": { + "External id": 233328,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115806159.354, "dur": 40.990, + "args": { + "External id": 233329,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115806206.951, "dur": 29.609, + "args": { + "External id": 233330,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115806242.552, "dur": 26.566, + "args": { + "External id": 233331,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115806273.271, "dur": 26.911, + "args": { + "External id": 233332,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115806304.931, "dur": 26.152, + "args": { + "External id": 233333,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115806338.354, "dur": 26.410, + "args": { + "External id": 233334,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115806380.802, "dur": 19.504, + "args": { + "External id": 233335,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 3446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115806415.210, "dur": 20.847, + "args": { + "External id": 233336,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115806447.920, "dur": 14.774, + "args": { + "External id": 233337,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 3448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115806475.837, "dur": 13.219, + "args": { + "External id": 233338,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 3449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115806519.292, "dur": 17.186, + "args": { + "External id": 233339,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 3450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115806606.156, "dur": 14.406, + "args": { + "External id": 233340,"Record function id": 0, "Ev Idx": 3451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115806609.325, "dur": 10.375, + "args": { + "External id": 233341,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115806613.601, "dur": 5.321, + "args": { + "External id": 233342,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115806614.959, "dur": 3.886, + "args": { + "External id": 233343,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115806624.258, "dur": 6.364, + "args": { + "External id": 233344,"Record function id": 0, "Ev Idx": 3455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115806625.615, "dur": 4.510, + "args": { + "External id": 233345,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115806626.628, "dur": 3.087, + "args": { + "External id": 233346,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115806627.052, "dur": 2.596, + "args": { + "External id": 233347,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115806644.557, "dur": 43.605, + "args": { + "External id": 233348,"Record function id": 0, "Ev Idx": 3459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115806647.725, "dur": 38.699, + "args": { + "External id": 233349,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115806649.057, "dur": 34.558, + "args": { + "External id": 233350,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115806649.582, "dur": 33.215, + "args": { + "External id": 233351,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115806695.015, "dur": 6.665, + "args": { + "External id": 233352,"Record function id": 0, "Ev Idx": 3463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115806697.111, "dur": 4.140, + "args": { + "External id": 233353,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115806698.682, "dur": 2.156, + "args": { + "External id": 233354,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115806699.444, "dur": 1.293, + "args": { + "External id": 233355,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115806704.814, "dur": 4.522, + "args": { + "External id": 233356,"Record function id": 0, "Ev Idx": 3467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115806706.475, "dur": 2.432, + "args": { + "External id": 233357,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115806706.964, "dur": 1.491, + "args": { + "External id": 233358,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115806707.685, "dur": 0.648, + "args": { + "External id": 233359,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115806712.321, "dur": 4.606, + "args": { + "External id": 233360,"Record function id": 0, "Ev Idx": 3471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115806713.746, "dur": 2.761, + "args": { + "External id": 233361,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115806714.438, "dur": 1.673, + "args": { + "External id": 233362,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115806715.266, "dur": 0.769, + "args": { + "External id": 233363,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115806720.141, "dur": 3.979, + "args": { + "External id": 233364,"Record function id": 0, "Ev Idx": 3475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115806721.363, "dur": 2.341, + "args": { + "External id": 233365,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115806721.853, "dur": 1.430, + "args": { + "External id": 233366,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115806722.554, "dur": 0.664, + "args": { + "External id": 233367,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115806727.115, "dur": 3.761, + "args": { + "External id": 233368,"Record function id": 0, "Ev Idx": 3479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115806728.268, "dur": 2.202, + "args": { + "External id": 233369,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115806728.733, "dur": 1.341, + "args": { + "External id": 233370,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115806729.148, "dur": 0.853, + "args": { + "External id": 233371,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115806733.873, "dur": 5.613, + "args": { + "External id": 233372,"Record function id": 0, "Ev Idx": 3483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115806735.095, "dur": 3.978, + "args": { + "External id": 233373,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115806735.539, "dur": 3.111, + "args": { + "External id": 233374,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115806735.861, "dur": 2.719, + "args": { + "External id": 233375,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115806743.374, "dur": 15108.802, + "args": { + "External id": 233376,"Record function id": 0, "Sequence number": 2757759, "Fwd thread id": 1, "Ev Idx": 3487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115806744.562, "dur": 15099.459, + "args": { + "External id": 233377,"Sequence number": 2757759, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 3488 + } + }, + { + "ph": "f", "id": 197, "pid": 4183440, "tid": 31337, "ts": 667115806744.562, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.7)", "pid": 4183440, "tid": 31337, + "ts": 667115806778.023, "dur": 39.180, + "args": { + "External id": 233378,"Record function id": 0, "Ev Idx": 3489 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.7)", "pid": 4183440, "tid": 31337, + "ts": 667115806824.806, "dur": 68.862, + "args": { + "External id": 233379,"Record function id": 0, "Ev Idx": 3490 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.7)", "pid": 4183440, "tid": 31337, + "ts": 667115806899.853, "dur": 14936.542, + "args": { + "External id": 233380,"Record function id": 0, "Ev Idx": 3491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115806990.613, "dur": 7.243, + "args": { + "External id": 233381,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115807006.901, "dur": 7.890, + "args": { + "External id": 233382,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 3493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115807027.920, "dur": 14106.171, + "args": { + "External id": 233383,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 3494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115807040.880, "dur": 14085.630, + "args": { + "External id": 233384,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 3495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115807064.775, "dur": 17.084, + "args": { + "External id": 233385,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115807085.773, "dur": 14006.885, + "args": { + "External id": 233386,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 3497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115807088.144, "dur": 14003.627, + "args": { + "External id": 233387,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 3498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115807092.106, "dur": 4.824, + "args": { + "External id": 233388,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115807098.590, "dur": 13989.446, + "args": { + "External id": 233389,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 3500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115821219.822, "dur": 9.189, + "args": { + "External id": 233390,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 3501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115821222.588, "dur": 6.125, + "args": { + "External id": 233391,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115821255.195, "dur": 262.134, + "args": { + "External id": 233392,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 3503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115821280.932, "dur": 231.358, + "args": { + "External id": 233393,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3504, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115821291.418, "dur": 198.928, + "args": { + "External id": 233394,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 3505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115821535.039, "dur": 2.343, + "args": { + "External id": 233395,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3506, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115821590.459, "dur": 5.914, + "args": { + "External id": 233396,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115821639.357, "dur": 1.346, + "args": { + "External id": 233397,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115821700.832, "dur": 3.730, + "args": { + "External id": 233398,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115821717.951, "dur": 1.016, + "args": { + "External id": 233399,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115821728.719, "dur": 0.666, + "args": { + "External id": 233400,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115821738.656, "dur": 1.247, + "args": { + "External id": 233401,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115821750.636, "dur": 2.865, + "args": { + "External id": 233402,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115821764.033, "dur": 1.619, + "args": { + "External id": 233403,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115821774.953, "dur": 0.720, + "args": { + "External id": 233404,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115821866.932, "dur": 2478.192, + "args": { + "External id": 233405,"Record function id": 0, "Ev Idx": 3516 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.6)", "pid": 4183440, "tid": 31337, + "ts": 667115821885.013, "dur": 951.262, + "args": { + "External id": 233406,"Record function id": 0, "Ev Idx": 3517 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 4183440, "tid": 31337, + "ts": 667115821899.352, "dur": 280.243, + "args": { + "External id": 233407,"Record function id": 0, "Ev Idx": 3518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115821972.721, "dur": 4.325, + "args": { + "External id": 233408,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 3519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115821979.802, "dur": 0.961, + "args": { + "External id": 233409,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 3520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115821982.468, "dur": 2.202, + "args": { + "External id": 233410,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115821986.451, "dur": 0.744, + "args": { + "External id": 233411,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115821988.828, "dur": 0.817, + "args": { + "External id": 233412,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115821991.184, "dur": 0.620, + "args": { + "External id": 233413,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115821993.534, "dur": 1.786, + "args": { + "External id": 233414,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 3525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115821997.009, "dur": 0.585, + "args": { + "External id": 233415,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115821998.957, "dur": 0.804, + "args": { + "External id": 233416,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115822001.419, "dur": 0.729, + "args": { + "External id": 233417,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115822019.779, "dur": 134.084, + "args": { + "External id": 233418,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 3529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115822034.706, "dur": 115.211, + "args": { + "External id": 233419,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 3530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115822047.606, "dur": 14.930, + "args": { + "External id": 233420,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115822065.166, "dur": 59.565, + "args": { + "External id": 233421,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 3532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115822067.600, "dur": 56.826, + "args": { + "External id": 233422,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 3533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822071.038, "dur": 5.394, + "args": { + "External id": 233423,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115822078.048, "dur": 45.720, + "args": { + "External id": 233424,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 3535 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.5", "pid": 4183440, "tid": 31337, + "ts": 667115822251.148, "dur": 576.954, + "args": { + "External id": 233425,"Record function id": 0, "Ev Idx": 3536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 4183440, "tid": 31337, + "ts": 667115822266.895, "dur": 549.169, + "args": { + "External id": 233426,"Record function id": 0, "Ev Idx": 3537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115822318.519, "dur": 4.725, + "args": { + "External id": 233427,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115822338.685, "dur": 27.324, + "args": { + "External id": 233428,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 3539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822342.994, "dur": 1.258, + "args": { + "External id": 233429,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822346.287, "dur": 0.716, + "args": { + "External id": 233430,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822348.636, "dur": 0.365, + "args": { + "External id": 233431,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822350.170, "dur": 0.624, + "args": { + "External id": 233432,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822351.925, "dur": 0.542, + "args": { + "External id": 233433,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822354.101, "dur": 2.433, + "args": { + "External id": 233434,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822357.761, "dur": 0.602, + "args": { + "External id": 233435,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822359.874, "dur": 0.957, + "args": { + "External id": 233436,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822361.855, "dur": 0.638, + "args": { + "External id": 233437,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115822375.774, "dur": 31.058, + "args": { + "External id": 233438,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 3549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115822434.554, "dur": 121.304, + "args": { + "External id": 233439,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 3550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115822443.251, "dur": 3.077, + "args": { + "External id": 233440,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115822451.670, "dur": 9.050, + "args": { + "External id": 233441,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 3552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115822455.273, "dur": 5.032, + "args": { + "External id": 233442,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 3553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822458.609, "dur": 0.659, + "args": { + "External id": 233443,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 3554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115822469.601, "dur": 43.521, + "args": { + "External id": 233444,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 3555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822471.832, "dur": 0.293, + "args": { + "External id": 233445,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822473.929, "dur": 0.452, + "args": { + "External id": 233446,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822475.446, "dur": 1.893, + "args": { + "External id": 233447,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822479.169, "dur": 0.271, + "args": { + "External id": 233448,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822480.947, "dur": 0.438, + "args": { + "External id": 233449,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822482.936, "dur": 0.404, + "args": { + "External id": 233450,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822484.441, "dur": 0.567, + "args": { + "External id": 233451,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822486.566, "dur": 0.410, + "args": { + "External id": 233452,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115822488.312, "dur": 0.419, + "args": { + "External id": 233453,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115822526.471, "dur": 22.035, + "args": { + "External id": 233454,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 3565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115822598.339, "dur": 147.122, + "args": { + "External id": 233455,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 3566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115822622.125, "dur": 119.734, + "args": { + "External id": 233456,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3567, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115822631.984, "dur": 105.128, + "args": { + "External id": 233457,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 3568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115822761.125, "dur": 1.965, + "args": { + "External id": 233458,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3569, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115822842.955, "dur": 1480.444, + "args": { + "External id": 233459,"Sequence number": 2757758, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 3570 + } + }, + { + "ph": "f", "id": 198, "pid": 4183440, "tid": 31337, "ts": 667115822842.955, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115822952.060, "dur": 97.772, + "args": { + "External id": 233460,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 3571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115823090.070, "dur": 36.440, + "args": { + "External id": 233461,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 3572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115823141.466, "dur": 39.150, + "args": { + "External id": 233462,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 3573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115823189.449, "dur": 24.952, + "args": { + "External id": 233463,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 3574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115823221.677, "dur": 31.807, + "args": { + "External id": 233464,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 3575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115823259.305, "dur": 20.013, + "args": { + "External id": 233465,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 3576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115823285.439, "dur": 27.917, + "args": { + "External id": 233466,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 3577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115823334.431, "dur": 22.650, + "args": { + "External id": 233467,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 3578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115823373.577, "dur": 26.819, + "args": { + "External id": 233468,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115823416.648, "dur": 17.772, + "args": { + "External id": 233469,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 3580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115823446.003, "dur": 13.170, + "args": { + "External id": 233470,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 3581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115823467.819, "dur": 54.070, + "args": { + "External id": 233471,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115823527.150, "dur": 31.865, + "args": { + "External id": 233472,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115823599.639, "dur": 208.389, + "args": { + "External id": 233473,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115823713.455, "dur": 6.660, + "args": { + "External id": 233474,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115823721.936, "dur": 5.351, + "args": { + "External id": 233475,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115823838.982, "dur": 24.846, + "args": { + "External id": 233476,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115823875.310, "dur": 13.459, + "args": { + "External id": 233477,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115823898.820, "dur": 52.436, + "args": { + "External id": 233478,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115823956.416, "dur": 30.684, + "args": { + "External id": 233479,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115823993.042, "dur": 26.538, + "args": { + "External id": 233480,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115824025.497, "dur": 27.711, + "args": { + "External id": 233481,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115824058.679, "dur": 25.555, + "args": { + "External id": 233482,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115824089.767, "dur": 27.132, + "args": { + "External id": 233483,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115824134.446, "dur": 22.309, + "args": { + "External id": 233484,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 3595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115824179.445, "dur": 23.068, + "args": { + "External id": 233485,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115824215.036, "dur": 15.641, + "args": { + "External id": 233486,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 3597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115824243.990, "dur": 12.460, + "args": { + "External id": 233487,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 3598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115824268.089, "dur": 15.112, + "args": { + "External id": 233488,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 3599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115824367.966, "dur": 14.445, + "args": { + "External id": 233489,"Record function id": 0, "Ev Idx": 3600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115824371.156, "dur": 10.291, + "args": { + "External id": 233490,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115824375.172, "dur": 5.567, + "args": { + "External id": 233491,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115824376.571, "dur": 4.080, + "args": { + "External id": 233492,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115824386.070, "dur": 3.867, + "args": { + "External id": 233493,"Record function id": 0, "Ev Idx": 3604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115824387.357, "dur": 2.144, + "args": { + "External id": 233494,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115824388.038, "dur": 1.092, + "args": { + "External id": 233495,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115824388.348, "dur": 0.708, + "args": { + "External id": 233496,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115824393.048, "dur": 3.862, + "args": { + "External id": 233497,"Record function id": 0, "Ev Idx": 3608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115824394.150, "dur": 2.350, + "args": { + "External id": 233498,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115824394.615, "dur": 1.515, + "args": { + "External id": 233499,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115824395.212, "dur": 0.838, + "args": { + "External id": 233500,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115824399.936, "dur": 3.812, + "args": { + "External id": 233501,"Record function id": 0, "Ev Idx": 3612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115824401.409, "dur": 1.924, + "args": { + "External id": 233502,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115824401.929, "dur": 1.037, + "args": { + "External id": 233503,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115824402.210, "dur": 0.651, + "args": { + "External id": 233504,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115824406.809, "dur": 3.515, + "args": { + "External id": 233505,"Record function id": 0, "Ev Idx": 3616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115824407.983, "dur": 1.899, + "args": { + "External id": 233506,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115824408.482, "dur": 1.026, + "args": { + "External id": 233507,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115824408.827, "dur": 0.589, + "args": { + "External id": 233508,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115824413.234, "dur": 7.064, + "args": { + "External id": 233509,"Record function id": 0, "Ev Idx": 3620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115824414.573, "dur": 5.269, + "args": { + "External id": 233510,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115824415.020, "dur": 4.421, + "args": { + "External id": 233511,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115824415.517, "dur": 0.725, + "args": { + "External id": 233512,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115824423.425, "dur": 5.779, + "args": { + "External id": 233513,"Record function id": 0, "Ev Idx": 3624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115824424.914, "dur": 3.868, + "args": { + "External id": 233514,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115824425.379, "dur": 3.021, + "args": { + "External id": 233515,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115824425.729, "dur": 2.568, + "args": { + "External id": 233516,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115824432.137, "dur": 4.122, + "args": { + "External id": 233517,"Record function id": 0, "Ev Idx": 3628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115824433.473, "dur": 2.362, + "args": { + "External id": 233518,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115824433.942, "dur": 1.527, + "args": { + "External id": 233519,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115824434.450, "dur": 0.918, + "args": { + "External id": 233520,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115824439.171, "dur": 3.542, + "args": { + "External id": 233521,"Record function id": 0, "Ev Idx": 3632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115824440.329, "dur": 1.944, + "args": { + "External id": 233522,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115824440.797, "dur": 1.098, + "args": { + "External id": 233523,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115824441.089, "dur": 0.732, + "args": { + "External id": 233524,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115824446.777, "dur": 14987.498, + "args": { + "External id": 233525,"Record function id": 0, "Sequence number": 2757757, "Fwd thread id": 1, "Ev Idx": 3636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115824448.133, "dur": 14977.885, + "args": { + "External id": 233526,"Sequence number": 2757757, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 3637 + } + }, + { + "ph": "f", "id": 199, "pid": 4183440, "tid": 31337, "ts": 667115824448.133, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.6)", "pid": 4183440, "tid": 31337, + "ts": 667115824479.996, "dur": 56.965, + "args": { + "External id": 233527,"Record function id": 0, "Ev Idx": 3638 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.6)", "pid": 4183440, "tid": 31337, + "ts": 667115824546.299, "dur": 63.521, + "args": { + "External id": 233528,"Record function id": 0, "Ev Idx": 3639 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.6)", "pid": 4183440, "tid": 31337, + "ts": 667115824616.472, "dur": 14801.411, + "args": { + "External id": 233529,"Record function id": 0, "Ev Idx": 3640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115824748.521, "dur": 7.534, + "args": { + "External id": 233530,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115824766.426, "dur": 8.492, + "args": { + "External id": 233531,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 3642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115824789.938, "dur": 13976.361, + "args": { + "External id": 233532,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 3643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115824803.458, "dur": 13953.247, + "args": { + "External id": 233533,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 3644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115824836.165, "dur": 13.785, + "args": { + "External id": 233534,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115824854.337, "dur": 13853.329, + "args": { + "External id": 233535,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 3646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115824856.711, "dur": 13849.964, + "args": { + "External id": 233536,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 3647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115824860.570, "dur": 4.835, + "args": { + "External id": 233537,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115824867.442, "dur": 13834.860, + "args": { + "External id": 233538,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 3649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115838863.201, "dur": 10.291, + "args": { + "External id": 233539,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 3650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115838866.275, "dur": 6.855, + "args": { + "External id": 233540,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115838902.255, "dur": 254.820, + "args": { + "External id": 233541,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 3652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115838927.937, "dur": 225.083, + "args": { + "External id": 233542,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3653, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115838939.401, "dur": 208.890, + "args": { + "External id": 233543,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 3654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115839173.428, "dur": 1.949, + "args": { + "External id": 233544,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3655, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115839226.414, "dur": 5.813, + "args": { + "External id": 233545,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115839273.962, "dur": 3.340, + "args": { + "External id": 233546,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115839292.034, "dur": 1.057, + "args": { + "External id": 233547,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115839304.399, "dur": 0.948, + "args": { + "External id": 233548,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115839315.518, "dur": 0.876, + "args": { + "External id": 233549,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115839325.107, "dur": 2.843, + "args": { + "External id": 233550,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115839338.098, "dur": 0.760, + "args": { + "External id": 233551,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115839349.126, "dur": 1.601, + "args": { + "External id": 233552,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115839360.040, "dur": 0.753, + "args": { + "External id": 233553,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115839447.142, "dur": 2552.068, + "args": { + "External id": 233554,"Record function id": 0, "Ev Idx": 3665 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.5)", "pid": 4183440, "tid": 31337, + "ts": 667115839464.610, "dur": 966.726, + "args": { + "External id": 233555,"Record function id": 0, "Ev Idx": 3666 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 4183440, "tid": 31337, + "ts": 667115839479.067, "dur": 354.231, + "args": { + "External id": 233556,"Record function id": 0, "Ev Idx": 3667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115839576.135, "dur": 6.128, + "args": { + "External id": 233557,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 3668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115839585.650, "dur": 0.934, + "args": { + "External id": 233558,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 3669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115839588.555, "dur": 0.704, + "args": { + "External id": 233559,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115839591.258, "dur": 0.882, + "args": { + "External id": 233560,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115839593.633, "dur": 0.723, + "args": { + "External id": 233561,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115839595.939, "dur": 0.760, + "args": { + "External id": 233562,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115839598.419, "dur": 1.688, + "args": { + "External id": 233563,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 3674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115839601.886, "dur": 0.791, + "args": { + "External id": 233564,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115839604.343, "dur": 2.204, + "args": { + "External id": 233565,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115839608.026, "dur": 0.621, + "args": { + "External id": 233566,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115839626.899, "dur": 173.259, + "args": { + "External id": 233567,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 3678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115839642.914, "dur": 152.506, + "args": { + "External id": 233568,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 3679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115839690.250, "dur": 12.924, + "args": { + "External id": 233569,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115839706.429, "dur": 62.673, + "args": { + "External id": 233570,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 3681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115839709.174, "dur": 59.659, + "args": { + "External id": 233571,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 3682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115839713.447, "dur": 5.799, + "args": { + "External id": 233572,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115839720.994, "dur": 47.311, + "args": { + "External id": 233573,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 3684 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.4", "pid": 4183440, "tid": 31337, + "ts": 667115839911.229, "dur": 512.407, + "args": { + "External id": 233574,"Record function id": 0, "Ev Idx": 3685 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 4183440, "tid": 31337, + "ts": 667115839928.245, "dur": 483.118, + "args": { + "External id": 233575,"Record function id": 0, "Ev Idx": 3686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115839984.725, "dur": 4.593, + "args": { + "External id": 233576,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115840005.763, "dur": 26.326, + "args": { + "External id": 233577,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 3688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840010.264, "dur": 1.427, + "args": { + "External id": 233578,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840013.051, "dur": 0.744, + "args": { + "External id": 233579,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840015.277, "dur": 0.406, + "args": { + "External id": 233580,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840016.670, "dur": 2.505, + "args": { + "External id": 233581,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840020.812, "dur": 0.537, + "args": { + "External id": 233582,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840022.881, "dur": 0.469, + "args": { + "External id": 233583,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840024.865, "dur": 0.293, + "args": { + "External id": 233584,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840026.201, "dur": 0.440, + "args": { + "External id": 233585,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840027.803, "dur": 0.524, + "args": { + "External id": 233586,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115840042.207, "dur": 30.497, + "args": { + "External id": 233587,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 3698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115840102.025, "dur": 91.995, + "args": { + "External id": 233588,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 3699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115840111.489, "dur": 3.327, + "args": { + "External id": 233589,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115840119.910, "dur": 9.113, + "args": { + "External id": 233590,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 3701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115840123.864, "dur": 4.765, + "args": { + "External id": 233591,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 3702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840126.767, "dur": 0.672, + "args": { + "External id": 233592,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 3703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115840135.918, "dur": 21.994, + "args": { + "External id": 233593,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 3704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840137.587, "dur": 1.731, + "args": { + "External id": 233594,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840140.596, "dur": 0.241, + "args": { + "External id": 233595,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840142.308, "dur": 0.543, + "args": { + "External id": 233596,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840144.221, "dur": 0.493, + "args": { + "External id": 233597,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840146.255, "dur": 0.574, + "args": { + "External id": 233598,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840147.993, "dur": 0.331, + "args": { + "External id": 233599,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840149.721, "dur": 0.302, + "args": { + "External id": 233600,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840151.339, "dur": 0.386, + "args": { + "External id": 233601,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115840152.954, "dur": 2.022, + "args": { + "External id": 233602,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115840167.768, "dur": 19.095, + "args": { + "External id": 233603,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 3714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115840236.464, "dur": 110.292, + "args": { + "External id": 233604,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 3715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115840259.470, "dur": 84.176, + "args": { + "External id": 233605,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3716, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115840268.705, "dur": 70.544, + "args": { + "External id": 233606,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 3717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115840361.492, "dur": 1.825, + "args": { + "External id": 233607,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3718, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115840438.737, "dur": 1539.483, + "args": { + "External id": 233608,"Sequence number": 2757756, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 3719 + } + }, + { + "ph": "f", "id": 200, "pid": 4183440, "tid": 31337, "ts": 667115840438.737, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115840570.876, "dur": 137.673, + "args": { + "External id": 233609,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 3720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115840754.154, "dur": 37.245, + "args": { + "External id": 233610,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 3721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115840809.020, "dur": 44.378, + "args": { + "External id": 233611,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 3722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115840862.348, "dur": 25.470, + "args": { + "External id": 233612,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 3723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115840893.407, "dur": 32.263, + "args": { + "External id": 233613,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 3724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115840931.985, "dur": 19.499, + "args": { + "External id": 233614,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 3725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115840960.041, "dur": 27.463, + "args": { + "External id": 233615,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 3726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115841009.611, "dur": 20.997, + "args": { + "External id": 233616,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 3727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115841049.628, "dur": 27.970, + "args": { + "External id": 233617,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115841096.239, "dur": 16.482, + "args": { + "External id": 233618,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 3729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115841124.037, "dur": 13.421, + "args": { + "External id": 233619,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 3730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115841144.647, "dur": 34.834, + "args": { + "External id": 233620,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115841182.841, "dur": 29.926, + "args": { + "External id": 233621,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115841239.524, "dur": 160.645, + "args": { + "External id": 233622,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115841311.770, "dur": 5.652, + "args": { + "External id": 233623,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115841319.396, "dur": 2.626, + "args": { + "External id": 233624,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115841427.973, "dur": 24.280, + "args": { + "External id": 233625,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115841466.047, "dur": 13.620, + "args": { + "External id": 233626,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115841486.790, "dur": 62.499, + "args": { + "External id": 233627,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115841557.154, "dur": 31.385, + "args": { + "External id": 233628,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115841596.756, "dur": 27.234, + "args": { + "External id": 233629,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115841628.235, "dur": 65.030, + "args": { + "External id": 233630,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115841702.990, "dur": 29.443, + "args": { + "External id": 233631,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115841738.936, "dur": 27.258, + "args": { + "External id": 233632,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115841784.856, "dur": 21.643, + "args": { + "External id": 233633,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 3744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115841823.432, "dur": 23.227, + "args": { + "External id": 233634,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115841859.576, "dur": 13.740, + "args": { + "External id": 233635,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 3746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115841888.045, "dur": 12.772, + "args": { + "External id": 233636,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 3747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115841912.330, "dur": 31.949, + "args": { + "External id": 233637,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 3748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115842022.648, "dur": 14.703, + "args": { + "External id": 233638,"Record function id": 0, "Ev Idx": 3749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115842025.766, "dur": 10.605, + "args": { + "External id": 233639,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115842029.715, "dur": 5.676, + "args": { + "External id": 233640,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115842031.114, "dur": 4.187, + "args": { + "External id": 233641,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115842040.990, "dur": 4.674, + "args": { + "External id": 233642,"Record function id": 0, "Ev Idx": 3753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115842042.464, "dur": 2.746, + "args": { + "External id": 233643,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115842043.336, "dur": 1.451, + "args": { + "External id": 233644,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115842043.783, "dur": 0.938, + "args": { + "External id": 233645,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115842049.104, "dur": 3.546, + "args": { + "External id": 233646,"Record function id": 0, "Ev Idx": 3757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115842050.335, "dur": 1.860, + "args": { + "External id": 233647,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115842050.796, "dur": 1.018, + "args": { + "External id": 233648,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115842051.075, "dur": 0.650, + "args": { + "External id": 233649,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115842055.708, "dur": 4.852, + "args": { + "External id": 233650,"Record function id": 0, "Ev Idx": 3761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115842057.058, "dur": 3.080, + "args": { + "External id": 233651,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115842057.687, "dur": 2.072, + "args": { + "External id": 233652,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115842058.200, "dur": 1.475, + "args": { + "External id": 233653,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115842063.558, "dur": 3.969, + "args": { + "External id": 233654,"Record function id": 0, "Ev Idx": 3765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115842064.736, "dur": 2.341, + "args": { + "External id": 233655,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115842065.246, "dur": 1.443, + "args": { + "External id": 233656,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115842065.650, "dur": 0.918, + "args": { + "External id": 233657,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115842070.485, "dur": 5.020, + "args": { + "External id": 233658,"Record function id": 0, "Ev Idx": 3769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115842071.942, "dur": 3.140, + "args": { + "External id": 233659,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115842073.035, "dur": 1.655, + "args": { + "External id": 233660,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115842073.910, "dur": 0.706, + "args": { + "External id": 233661,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115842078.546, "dur": 3.595, + "args": { + "External id": 233662,"Record function id": 0, "Ev Idx": 3773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115842079.547, "dur": 2.179, + "args": { + "External id": 233663,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115842080.076, "dur": 1.243, + "args": { + "External id": 233664,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115842080.644, "dur": 0.600, + "args": { + "External id": 233665,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115842085.007, "dur": 6.764, + "args": { + "External id": 233666,"Record function id": 0, "Ev Idx": 3777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115842086.052, "dur": 5.295, + "args": { + "External id": 233667,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115842086.556, "dur": 4.402, + "args": { + "External id": 233668,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115842087.203, "dur": 3.679, + "args": { + "External id": 233669,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115842094.791, "dur": 3.285, + "args": { + "External id": 233670,"Record function id": 0, "Ev Idx": 3781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115842095.695, "dur": 1.958, + "args": { + "External id": 233671,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115842096.145, "dur": 1.133, + "args": { + "External id": 233672,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115842096.518, "dur": 0.684, + "args": { + "External id": 233673,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115842101.648, "dur": 15274.679, + "args": { + "External id": 233674,"Record function id": 0, "Sequence number": 2757755, "Fwd thread id": 1, "Ev Idx": 3785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115842102.834, "dur": 15265.210, + "args": { + "External id": 233675,"Sequence number": 2757755, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 3786 + } + }, + { + "ph": "f", "id": 201, "pid": 4183440, "tid": 31337, "ts": 667115842102.834, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.5)", "pid": 4183440, "tid": 31337, + "ts": 667115842131.985, "dur": 39.718, + "args": { + "External id": 233676,"Record function id": 0, "Ev Idx": 3787 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.5)", "pid": 4183440, "tid": 31337, + "ts": 667115842179.413, "dur": 66.415, + "args": { + "External id": 233677,"Record function id": 0, "Ev Idx": 3788 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.5)", "pid": 4183440, "tid": 31337, + "ts": 667115842252.190, "dur": 15108.529, + "args": { + "External id": 233678,"Record function id": 0, "Ev Idx": 3789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115842337.360, "dur": 9.447, + "args": { + "External id": 233679,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115842355.829, "dur": 4.402, + "args": { + "External id": 233680,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 3791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115842372.994, "dur": 14307.411, + "args": { + "External id": 233681,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 3792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115842386.159, "dur": 14261.547, + "args": { + "External id": 233682,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 3793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115842414.787, "dur": 13.992, + "args": { + "External id": 233683,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115842432.724, "dur": 14180.602, + "args": { + "External id": 233684,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 3795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115842435.352, "dur": 14177.029, + "args": { + "External id": 233685,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 3796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115842439.184, "dur": 4.548, + "args": { + "External id": 233686,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115842445.794, "dur": 14162.560, + "args": { + "External id": 233687,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 3798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115856773.097, "dur": 9.409, + "args": { + "External id": 233688,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 3799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115856775.909, "dur": 6.206, + "args": { + "External id": 233689,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115856810.362, "dur": 288.998, + "args": { + "External id": 233690,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 3801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115856834.436, "dur": 260.633, + "args": { + "External id": 233691,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3802, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115856845.903, "dur": 244.224, + "args": { + "External id": 233692,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 3803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115857113.691, "dur": 2.045, + "args": { + "External id": 233693,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3804, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857167.413, "dur": 6.081, + "args": { + "External id": 233694,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857217.459, "dur": 1.078, + "args": { + "External id": 233695,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857234.328, "dur": 1.213, + "args": { + "External id": 233696,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857247.888, "dur": 1.617, + "args": { + "External id": 233697,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857258.785, "dur": 0.824, + "args": { + "External id": 233698,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857268.870, "dur": 1.012, + "args": { + "External id": 233699,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857279.338, "dur": 0.737, + "args": { + "External id": 233700,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857290.994, "dur": 2.786, + "args": { + "External id": 233701,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857302.435, "dur": 0.754, + "args": { + "External id": 233702,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115857389.795, "dur": 2485.790, + "args": { + "External id": 233703,"Record function id": 0, "Ev Idx": 3814 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.4)", "pid": 4183440, "tid": 31337, + "ts": 667115857408.591, "dur": 935.330, + "args": { + "External id": 233704,"Record function id": 0, "Ev Idx": 3815 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 4183440, "tid": 31337, + "ts": 667115857424.130, "dur": 341.972, + "args": { + "External id": 233705,"Record function id": 0, "Ev Idx": 3816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115857514.121, "dur": 4.717, + "args": { + "External id": 233706,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 3817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115857522.281, "dur": 0.823, + "args": { + "External id": 233707,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 3818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115857524.966, "dur": 0.854, + "args": { + "External id": 233708,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115857527.498, "dur": 0.636, + "args": { + "External id": 233709,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115857529.579, "dur": 2.226, + "args": { + "External id": 233710,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115857533.289, "dur": 0.728, + "args": { + "External id": 233711,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115857535.535, "dur": 1.428, + "args": { + "External id": 233712,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 3823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115857538.509, "dur": 0.823, + "args": { + "External id": 233713,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115857540.758, "dur": 0.531, + "args": { + "External id": 233714,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115857542.927, "dur": 0.805, + "args": { + "External id": 233715,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115857562.293, "dur": 171.115, + "args": { + "External id": 233716,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 3827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115857578.197, "dur": 150.661, + "args": { + "External id": 233717,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 3828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115857591.309, "dur": 12.681, + "args": { + "External id": 233718,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115857606.842, "dur": 95.106, + "args": { + "External id": 233719,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 3830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115857609.253, "dur": 92.151, + "args": { + "External id": 233720,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 3831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857612.672, "dur": 5.369, + "args": { + "External id": 233721,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115857619.616, "dur": 80.821, + "args": { + "External id": 233722,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 3833 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.3", "pid": 4183440, "tid": 31337, + "ts": 667115857846.404, "dur": 490.084, + "args": { + "External id": 233723,"Record function id": 0, "Ev Idx": 3834 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 4183440, "tid": 31337, + "ts": 667115857863.688, "dur": 460.769, + "args": { + "External id": 233724,"Record function id": 0, "Ev Idx": 3835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115857920.518, "dur": 6.555, + "args": { + "External id": 233725,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115857944.092, "dur": 25.041, + "args": { + "External id": 233726,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 3837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857948.524, "dur": 1.672, + "args": { + "External id": 233727,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857951.883, "dur": 0.455, + "args": { + "External id": 233728,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857953.875, "dur": 0.359, + "args": { + "External id": 233729,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857955.790, "dur": 0.187, + "args": { + "External id": 233730,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857957.367, "dur": 0.299, + "args": { + "External id": 233731,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857958.504, "dur": 0.428, + "args": { + "External id": 233732,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857960.205, "dur": 0.283, + "args": { + "External id": 233733,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857961.623, "dur": 1.355, + "args": { + "External id": 233734,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115857964.727, "dur": 0.408, + "args": { + "External id": 233735,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115857978.979, "dur": 29.293, + "args": { + "External id": 233736,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 3847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115858036.576, "dur": 83.168, + "args": { + "External id": 233737,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 3848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115858045.880, "dur": 2.692, + "args": { + "External id": 233738,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115858053.659, "dur": 9.533, + "args": { + "External id": 233739,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 3850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115858057.810, "dur": 4.946, + "args": { + "External id": 233740,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 3851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115858060.967, "dur": 0.640, + "args": { + "External id": 233741,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 3852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115858069.046, "dur": 17.040, + "args": { + "External id": 233742,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 3853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115858070.562, "dur": 0.298, + "args": { + "External id": 233743,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115858072.003, "dur": 0.310, + "args": { + "External id": 233744,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115858073.519, "dur": 0.336, + "args": { + "External id": 233745,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115858074.918, "dur": 0.270, + "args": { + "External id": 233746,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115858076.054, "dur": 1.886, + "args": { + "External id": 233747,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115858079.099, "dur": 0.439, + "args": { + "External id": 233748,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115858080.580, "dur": 0.373, + "args": { + "External id": 233749,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115858081.933, "dur": 0.413, + "args": { + "External id": 233750,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115858083.370, "dur": 0.351, + "args": { + "External id": 233751,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115858094.834, "dur": 18.045, + "args": { + "External id": 233752,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 3863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115858160.157, "dur": 104.298, + "args": { + "External id": 233753,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 3864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115858181.227, "dur": 79.737, + "args": { + "External id": 233754,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3865, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115858190.237, "dur": 66.930, + "args": { + "External id": 233755,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 3866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115858276.933, "dur": 1.857, + "args": { + "External id": 233756,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3867, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115858350.660, "dur": 1500.342, + "args": { + "External id": 233757,"Sequence number": 2757754, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 3868 + } + }, + { + "ph": "f", "id": 202, "pid": 4183440, "tid": 31337, "ts": 667115858350.660, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115858453.829, "dur": 118.465, + "args": { + "External id": 233758,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 3869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115858615.020, "dur": 72.779, + "args": { + "External id": 233759,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 3870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115858707.850, "dur": 47.725, + "args": { + "External id": 233760,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 3871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115858765.597, "dur": 26.841, + "args": { + "External id": 233761,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 3872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115858798.227, "dur": 32.916, + "args": { + "External id": 233762,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 3873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115858838.660, "dur": 19.937, + "args": { + "External id": 233763,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 3874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115858865.734, "dur": 28.009, + "args": { + "External id": 233764,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 3875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115858915.976, "dur": 24.066, + "args": { + "External id": 233765,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 3876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115858956.072, "dur": 28.928, + "args": { + "External id": 233766,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115859002.853, "dur": 18.289, + "args": { + "External id": 233767,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 3878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115859032.155, "dur": 15.526, + "args": { + "External id": 233768,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 3879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115859056.054, "dur": 34.767, + "args": { + "External id": 233769,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115859093.784, "dur": 29.395, + "args": { + "External id": 233770,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115859148.300, "dur": 161.555, + "args": { + "External id": 233771,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115859221.252, "dur": 5.618, + "args": { + "External id": 233772,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115859228.701, "dur": 2.926, + "args": { + "External id": 233773,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115859337.261, "dur": 23.099, + "args": { + "External id": 233774,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115859370.618, "dur": 13.602, + "args": { + "External id": 233775,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115859390.918, "dur": 37.743, + "args": { + "External id": 233776,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115859435.646, "dur": 31.312, + "args": { + "External id": 233777,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115859472.430, "dur": 42.144, + "args": { + "External id": 233778,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115859521.528, "dur": 30.944, + "args": { + "External id": 233779,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115859558.556, "dur": 26.203, + "args": { + "External id": 233780,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 3891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115859591.739, "dur": 26.503, + "args": { + "External id": 233781,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 3892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115859635.347, "dur": 55.085, + "args": { + "External id": 233782,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 3893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115859709.243, "dur": 23.463, + "args": { + "External id": 233783,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115859745.197, "dur": 15.132, + "args": { + "External id": 233784,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 3895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115859773.974, "dur": 14.786, + "args": { + "External id": 233785,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 3896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115859799.931, "dur": 15.815, + "args": { + "External id": 233786,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 3897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115859897.964, "dur": 14.688, + "args": { + "External id": 233787,"Record function id": 0, "Ev Idx": 3898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115859901.335, "dur": 10.368, + "args": { + "External id": 233788,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115859905.756, "dur": 5.176, + "args": { + "External id": 233789,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115859906.977, "dur": 3.869, + "args": { + "External id": 233790,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115859916.112, "dur": 4.564, + "args": { + "External id": 233791,"Record function id": 0, "Ev Idx": 3902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115859917.561, "dur": 2.629, + "args": { + "External id": 233792,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115859918.368, "dur": 1.410, + "args": { + "External id": 233793,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115859918.816, "dur": 0.897, + "args": { + "External id": 233794,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115859923.892, "dur": 4.399, + "args": { + "External id": 233795,"Record function id": 0, "Ev Idx": 3906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115859925.419, "dur": 2.430, + "args": { + "External id": 233796,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115859926.214, "dur": 1.252, + "args": { + "External id": 233797,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115859926.810, "dur": 0.570, + "args": { + "External id": 233798,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 3909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115859931.370, "dur": 4.757, + "args": { + "External id": 233799,"Record function id": 0, "Ev Idx": 3910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115859932.608, "dur": 3.072, + "args": { + "External id": 233800,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115859933.276, "dur": 1.992, + "args": { + "External id": 233801,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115859933.560, "dur": 1.636, + "args": { + "External id": 233802,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 3913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115859939.075, "dur": 4.259, + "args": { + "External id": 233803,"Record function id": 0, "Ev Idx": 3914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115859940.359, "dur": 2.534, + "args": { + "External id": 233804,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115859940.971, "dur": 1.523, + "args": { + "External id": 233805,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115859941.672, "dur": 0.744, + "args": { + "External id": 233806,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115859949.310, "dur": 3.471, + "args": { + "External id": 233807,"Record function id": 0, "Ev Idx": 3918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115859950.309, "dur": 2.045, + "args": { + "External id": 233808,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115859950.776, "dur": 1.198, + "args": { + "External id": 233809,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115859951.240, "dur": 0.632, + "args": { + "External id": 233810,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115859955.863, "dur": 3.307, + "args": { + "External id": 233811,"Record function id": 0, "Ev Idx": 3922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115859956.992, "dur": 1.741, + "args": { + "External id": 233812,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115859957.446, "dur": 0.913, + "args": { + "External id": 233813,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115859957.787, "dur": 0.469, + "args": { + "External id": 233814,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115859962.099, "dur": 3.459, + "args": { + "External id": 233815,"Record function id": 0, "Ev Idx": 3926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115859963.354, "dur": 1.784, + "args": { + "External id": 233816,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115859963.823, "dur": 0.912, + "args": { + "External id": 233817,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115859964.117, "dur": 0.547, + "args": { + "External id": 233818,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 3929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115859968.463, "dur": 6.024, + "args": { + "External id": 233819,"Record function id": 0, "Ev Idx": 3930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115859969.882, "dur": 4.159, + "args": { + "External id": 233820,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115859970.387, "dur": 3.273, + "args": { + "External id": 233821,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115859973.105, "dur": 0.449, + "args": { + "External id": 233822,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 3933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115859979.390, "dur": 14888.863, + "args": { + "External id": 233823,"Record function id": 0, "Sequence number": 2757753, "Fwd thread id": 1, "Ev Idx": 3934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115859980.558, "dur": 14878.814, + "args": { + "External id": 233824,"Sequence number": 2757753, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 3935 + } + }, + { + "ph": "f", "id": 203, "pid": 4183440, "tid": 31337, "ts": 667115859980.558, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.4)", "pid": 4183440, "tid": 31337, + "ts": 667115860013.096, "dur": 38.293, + "args": { + "External id": 233825,"Record function id": 0, "Ev Idx": 3936 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.4)", "pid": 4183440, "tid": 31337, + "ts": 667115860058.888, "dur": 68.317, + "args": { + "External id": 233826,"Record function id": 0, "Ev Idx": 3937 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.4)", "pid": 4183440, "tid": 31337, + "ts": 667115860132.873, "dur": 14718.373, + "args": { + "External id": 233827,"Record function id": 0, "Ev Idx": 3938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115860217.959, "dur": 6.205, + "args": { + "External id": 233828,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115860233.148, "dur": 4.566, + "args": { + "External id": 233829,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 3940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115860250.742, "dur": 13909.344, + "args": { + "External id": 233830,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 3941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115860263.110, "dur": 13889.021, + "args": { + "External id": 233831,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 3942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115860287.535, "dur": 14.770, + "args": { + "External id": 233832,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115860307.078, "dur": 13810.928, + "args": { + "External id": 233833,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 3944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115860309.666, "dur": 13807.514, + "args": { + "External id": 233834,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 3945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115860313.521, "dur": 4.445, + "args": { + "External id": 233835,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115860319.596, "dur": 13794.264, + "args": { + "External id": 233836,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 3947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115874246.202, "dur": 8.908, + "args": { + "External id": 233837,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 3948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115874248.954, "dur": 5.815, + "args": { + "External id": 233838,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115874283.024, "dur": 261.542, + "args": { + "External id": 233839,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 3950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115874306.441, "dur": 233.400, + "args": { + "External id": 233840,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3951, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115874317.049, "dur": 217.196, + "args": { + "External id": 233841,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 3952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115874561.873, "dur": 1.984, + "args": { + "External id": 233842,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3953, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115874618.363, "dur": 5.848, + "args": { + "External id": 233843,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115874703.532, "dur": 2.295, + "args": { + "External id": 233844,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115874723.005, "dur": 1.498, + "args": { + "External id": 233845,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115874736.198, "dur": 2.689, + "args": { + "External id": 233846,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115874748.796, "dur": 0.821, + "args": { + "External id": 233847,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115874758.807, "dur": 0.804, + "args": { + "External id": 233848,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115874768.940, "dur": 0.541, + "args": { + "External id": 233849,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115874779.791, "dur": 3.091, + "args": { + "External id": 233850,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115874791.974, "dur": 0.735, + "args": { + "External id": 233851,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115874882.797, "dur": 2477.539, + "args": { + "External id": 233852,"Record function id": 0, "Ev Idx": 3963 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.3)", "pid": 4183440, "tid": 31337, + "ts": 667115874901.255, "dur": 958.365, + "args": { + "External id": 233853,"Record function id": 0, "Ev Idx": 3964 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 4183440, "tid": 31337, + "ts": 667115874916.621, "dur": 281.332, + "args": { + "External id": 233854,"Record function id": 0, "Ev Idx": 3965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115874991.271, "dur": 4.068, + "args": { + "External id": 233855,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 3966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115874998.179, "dur": 1.014, + "args": { + "External id": 233856,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 3967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115875000.943, "dur": 0.928, + "args": { + "External id": 233857,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115875003.544, "dur": 0.747, + "args": { + "External id": 233858,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115875006.025, "dur": 2.039, + "args": { + "External id": 233859,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115875009.537, "dur": 0.721, + "args": { + "External id": 233860,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 3971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115875011.801, "dur": 1.223, + "args": { + "External id": 233861,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 3972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115875014.264, "dur": 0.872, + "args": { + "External id": 233862,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115875016.817, "dur": 0.557, + "args": { + "External id": 233863,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115875018.985, "dur": 0.567, + "args": { + "External id": 233864,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 3975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115875036.743, "dur": 134.761, + "args": { + "External id": 233865,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 3976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115875052.199, "dur": 115.155, + "args": { + "External id": 233866,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 3977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115875064.152, "dur": 12.702, + "args": { + "External id": 233867,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115875079.740, "dur": 60.595, + "args": { + "External id": 233868,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 3979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115875082.140, "dur": 57.751, + "args": { + "External id": 233869,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 3980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875086.180, "dur": 5.820, + "args": { + "External id": 233870,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115875093.672, "dur": 45.599, + "args": { + "External id": 233871,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 3982 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.2", "pid": 4183440, "tid": 31337, + "ts": 667115875273.218, "dur": 578.602, + "args": { + "External id": 233872,"Record function id": 0, "Ev Idx": 3983 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 4183440, "tid": 31337, + "ts": 667115875289.003, "dur": 550.356, + "args": { + "External id": 233873,"Record function id": 0, "Ev Idx": 3984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115875344.003, "dur": 5.075, + "args": { + "External id": 233874,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115875364.563, "dur": 26.826, + "args": { + "External id": 233875,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 3986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875369.004, "dur": 1.803, + "args": { + "External id": 233876,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875372.453, "dur": 1.077, + "args": { + "External id": 233877,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875374.760, "dur": 0.886, + "args": { + "External id": 233878,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875377.220, "dur": 0.732, + "args": { + "External id": 233879,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875379.655, "dur": 0.598, + "args": { + "External id": 233880,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875381.168, "dur": 0.645, + "args": { + "External id": 233881,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875383.234, "dur": 0.743, + "args": { + "External id": 233882,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875385.129, "dur": 1.385, + "args": { + "External id": 233883,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875388.222, "dur": 0.505, + "args": { + "External id": 233884,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 3995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115875401.500, "dur": 30.339, + "args": { + "External id": 233885,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 3996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115875460.626, "dur": 116.901, + "args": { + "External id": 233886,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 3997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115875469.224, "dur": 3.111, + "args": { + "External id": 233887,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115875476.775, "dur": 9.539, + "args": { + "External id": 233888,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 3999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115875480.555, "dur": 5.375, + "args": { + "External id": 233889,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 4000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875484.124, "dur": 0.842, + "args": { + "External id": 233890,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 4001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115875512.577, "dur": 24.635, + "args": { + "External id": 233891,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 4002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875514.879, "dur": 1.260, + "args": { + "External id": 233892,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875517.961, "dur": 0.802, + "args": { + "External id": 233893,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875520.433, "dur": 0.635, + "args": { + "External id": 233894,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875522.354, "dur": 0.508, + "args": { + "External id": 233895,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875524.846, "dur": 0.524, + "args": { + "External id": 233896,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875526.411, "dur": 1.139, + "args": { + "External id": 233897,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875528.886, "dur": 0.645, + "args": { + "External id": 233898,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875530.487, "dur": 0.686, + "args": { + "External id": 233899,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115875532.573, "dur": 0.767, + "args": { + "External id": 233900,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115875547.659, "dur": 22.194, + "args": { + "External id": 233901,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 4012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115875621.315, "dur": 147.858, + "args": { + "External id": 233902,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 4013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115875643.167, "dur": 122.024, + "args": { + "External id": 233903,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4014, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115875688.448, "dur": 72.814, + "args": { + "External id": 233904,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 4015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115875784.596, "dur": 1.815, + "args": { + "External id": 233905,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4016, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115875866.742, "dur": 1471.042, + "args": { + "External id": 233906,"Sequence number": 2757752, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 4017 + } + }, + { + "ph": "f", "id": 204, "pid": 4183440, "tid": 31337, "ts": 667115875866.742, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115875975.933, "dur": 99.301, + "args": { + "External id": 233907,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 4018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115876112.045, "dur": 37.480, + "args": { + "External id": 233908,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 4019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115876165.084, "dur": 40.021, + "args": { + "External id": 233909,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 4020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115876214.262, "dur": 26.236, + "args": { + "External id": 233910,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 4021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115876246.535, "dur": 31.574, + "args": { + "External id": 233911,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 4022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115876284.938, "dur": 19.306, + "args": { + "External id": 233912,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 4023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115876311.125, "dur": 28.060, + "args": { + "External id": 233913,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 4024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115876361.844, "dur": 22.441, + "args": { + "External id": 233914,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 4025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115876401.214, "dur": 28.564, + "args": { + "External id": 233915,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115876447.401, "dur": 17.462, + "args": { + "External id": 233916,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 4027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115876477.495, "dur": 32.151, + "args": { + "External id": 233917,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 4028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115876521.359, "dur": 39.319, + "args": { + "External id": 233918,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 4029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115876563.912, "dur": 30.006, + "args": { + "External id": 233919,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115876618.736, "dur": 201.725, + "args": { + "External id": 233920,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115876730.613, "dur": 6.225, + "args": { + "External id": 233921,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115876738.957, "dur": 2.800, + "args": { + "External id": 233922,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115876851.625, "dur": 24.861, + "args": { + "External id": 233923,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115876888.343, "dur": 13.946, + "args": { + "External id": 233924,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115876909.996, "dur": 46.349, + "args": { + "External id": 233925,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 4036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115876962.081, "dur": 30.062, + "args": { + "External id": 233926,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115876998.699, "dur": 26.580, + "args": { + "External id": 233927,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 4038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115877029.848, "dur": 26.942, + "args": { + "External id": 233928,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115877062.817, "dur": 26.079, + "args": { + "External id": 233929,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 4040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115877095.971, "dur": 27.080, + "args": { + "External id": 233930,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115877139.843, "dur": 20.335, + "args": { + "External id": 233931,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 4042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115877176.557, "dur": 22.339, + "args": { + "External id": 233932,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115877212.573, "dur": 16.102, + "args": { + "External id": 233933,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 4044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115877243.814, "dur": 27.705, + "args": { + "External id": 233934,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 4045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115877292.636, "dur": 16.694, + "args": { + "External id": 233935,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 4046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115877380.942, "dur": 14.610, + "args": { + "External id": 233936,"Record function id": 0, "Ev Idx": 4047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115877383.827, "dur": 10.733, + "args": { + "External id": 233937,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115877387.994, "dur": 5.759, + "args": { + "External id": 233938,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115877389.747, "dur": 3.913, + "args": { + "External id": 233939,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115877399.429, "dur": 4.618, + "args": { + "External id": 233940,"Record function id": 0, "Ev Idx": 4051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115877400.795, "dur": 2.805, + "args": { + "External id": 233941,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115877401.453, "dur": 1.707, + "args": { + "External id": 233942,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115877402.066, "dur": 0.965, + "args": { + "External id": 233943,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115877407.398, "dur": 7.791, + "args": { + "External id": 233944,"Record function id": 0, "Ev Idx": 4055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115877408.783, "dur": 6.001, + "args": { + "External id": 233945,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115877412.558, "dur": 1.807, + "args": { + "External id": 233946,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115877413.325, "dur": 0.956, + "args": { + "External id": 233947,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115877418.306, "dur": 5.062, + "args": { + "External id": 233948,"Record function id": 0, "Ev Idx": 4059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115877420.115, "dur": 2.796, + "args": { + "External id": 233949,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 4060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115877421.045, "dur": 1.469, + "args": { + "External id": 233950,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 4061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115877421.605, "dur": 0.807, + "args": { + "External id": 233951,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 4062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115877426.406, "dur": 4.451, + "args": { + "External id": 233952,"Record function id": 0, "Ev Idx": 4063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115877427.662, "dur": 2.789, + "args": { + "External id": 233953,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115877428.141, "dur": 1.892, + "args": { + "External id": 233954,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115877428.940, "dur": 0.997, + "args": { + "External id": 233955,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115877433.959, "dur": 4.167, + "args": { + "External id": 233956,"Record function id": 0, "Ev Idx": 4067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115877435.078, "dur": 2.648, + "args": { + "External id": 233957,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115877435.558, "dur": 1.759, + "args": { + "External id": 233958,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115877436.379, "dur": 0.833, + "args": { + "External id": 233959,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115877441.271, "dur": 4.295, + "args": { + "External id": 233960,"Record function id": 0, "Ev Idx": 4071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115877442.420, "dur": 2.724, + "args": { + "External id": 233961,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115877443.411, "dur": 1.318, + "args": { + "External id": 233962,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115877443.943, "dur": 0.675, + "args": { + "External id": 233963,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115877448.548, "dur": 3.943, + "args": { + "External id": 233964,"Record function id": 0, "Ev Idx": 4075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115877449.413, "dur": 2.665, + "args": { + "External id": 233965,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115877449.886, "dur": 1.780, + "args": { + "External id": 233966,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115877450.657, "dur": 0.914, + "args": { + "External id": 233967,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115877455.581, "dur": 4.061, + "args": { + "External id": 233968,"Record function id": 0, "Ev Idx": 4079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115877456.760, "dur": 2.480, + "args": { + "External id": 233969,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115877457.234, "dur": 1.584, + "args": { + "External id": 233970,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115877457.724, "dur": 0.997, + "args": { + "External id": 233971,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115877463.403, "dur": 15051.311, + "args": { + "External id": 233972,"Record function id": 0, "Sequence number": 2757751, "Fwd thread id": 1, "Ev Idx": 4083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115877464.766, "dur": 15024.383, + "args": { + "External id": 233973,"Sequence number": 2757751, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 4084 + } + }, + { + "ph": "f", "id": 205, "pid": 4183440, "tid": 31337, "ts": 667115877464.766, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.3)", "pid": 4183440, "tid": 31337, + "ts": 667115877508.620, "dur": 36.870, + "args": { + "External id": 233974,"Record function id": 0, "Ev Idx": 4085 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.3)", "pid": 4183440, "tid": 31337, + "ts": 667115877554.426, "dur": 61.658, + "args": { + "External id": 233975,"Record function id": 0, "Ev Idx": 4086 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.3)", "pid": 4183440, "tid": 31337, + "ts": 667115877622.165, "dur": 14859.634, + "args": { + "External id": 233976,"Record function id": 0, "Ev Idx": 4087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115877746.836, "dur": 7.601, + "args": { + "External id": 233977,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115877764.189, "dur": 5.050, + "args": { + "External id": 233978,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 4089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115877786.607, "dur": 14070.251, + "args": { + "External id": 233979,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 4090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115877799.980, "dur": 14048.513, + "args": { + "External id": 233980,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 4091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115877821.297, "dur": 16.476, + "args": { + "External id": 233981,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115877842.067, "dur": 13972.849, + "args": { + "External id": 233982,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 4093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115877844.498, "dur": 13969.668, + "args": { + "External id": 233983,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 4094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115877848.082, "dur": 5.086, + "args": { + "External id": 233984,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115877867.071, "dur": 13943.203, + "args": { + "External id": 233985,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 4096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115891942.906, "dur": 9.187, + "args": { + "External id": 233986,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 4097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115891945.688, "dur": 6.025, + "args": { + "External id": 233987,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115891979.854, "dur": 244.768, + "args": { + "External id": 233988,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 4099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115892004.825, "dur": 215.733, + "args": { + "External id": 233989,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4100, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115892015.401, "dur": 200.512, + "args": { + "External id": 233990,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 4101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115892239.515, "dur": 1.811, + "args": { + "External id": 233991,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4102, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115892289.152, "dur": 5.696, + "args": { + "External id": 233992,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115892335.884, "dur": 1.386, + "args": { + "External id": 233993,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115892351.902, "dur": 1.199, + "args": { + "External id": 233994,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115892364.746, "dur": 0.939, + "args": { + "External id": 233995,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115892376.472, "dur": 1.055, + "args": { + "External id": 233996,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115892387.350, "dur": 1.009, + "args": { + "External id": 233997,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115892401.836, "dur": 0.790, + "args": { + "External id": 233998,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115892414.337, "dur": 1.697, + "args": { + "External id": 233999,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115892425.834, "dur": 0.778, + "args": { + "External id": 234000,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115892530.033, "dur": 2528.032, + "args": { + "External id": 234001,"Record function id": 0, "Ev Idx": 4112 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.2)", "pid": 4183440, "tid": 31337, + "ts": 667115892550.454, "dur": 935.389, + "args": { + "External id": 234002,"Record function id": 0, "Ev Idx": 4113 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 4183440, "tid": 31337, + "ts": 667115892565.793, "dur": 327.132, + "args": { + "External id": 234003,"Record function id": 0, "Ev Idx": 4114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115892641.589, "dur": 4.405, + "args": { + "External id": 234004,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 4115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115892649.192, "dur": 1.221, + "args": { + "External id": 234005,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115892686.381, "dur": 1.536, + "args": { + "External id": 234006,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115892690.281, "dur": 1.265, + "args": { + "External id": 234007,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115892693.387, "dur": 0.805, + "args": { + "External id": 234008,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115892695.882, "dur": 1.124, + "args": { + "External id": 234009,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115892698.611, "dur": 1.337, + "args": { + "External id": 234010,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115892701.550, "dur": 1.484, + "args": { + "External id": 234011,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115892704.857, "dur": 1.197, + "args": { + "External id": 234012,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115892707.788, "dur": 1.476, + "args": { + "External id": 234013,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115892727.594, "dur": 135.673, + "args": { + "External id": 234014,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 4125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115892743.052, "dur": 116.389, + "args": { + "External id": 234015,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 4126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115892755.460, "dur": 13.829, + "args": { + "External id": 234016,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115892772.106, "dur": 61.432, + "args": { + "External id": 234017,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 4128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115892774.702, "dur": 58.479, + "args": { + "External id": 234018,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 4129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115892778.304, "dur": 6.239, + "args": { + "External id": 234019,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115892786.190, "dur": 46.317, + "args": { + "External id": 234020,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 4131 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.1", "pid": 4183440, "tid": 31337, + "ts": 667115892973.829, "dur": 504.789, + "args": { + "External id": 234021,"Record function id": 0, "Ev Idx": 4132 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 4183440, "tid": 31337, + "ts": 667115892990.008, "dur": 476.748, + "args": { + "External id": 234022,"Record function id": 0, "Ev Idx": 4133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115893047.637, "dur": 4.764, + "args": { + "External id": 234023,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115893067.581, "dur": 33.480, + "args": { + "External id": 234024,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 4135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893071.847, "dur": 1.299, + "args": { + "External id": 234025,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893074.950, "dur": 0.606, + "args": { + "External id": 234026,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893076.715, "dur": 0.674, + "args": { + "External id": 234027,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893079.705, "dur": 0.651, + "args": { + "External id": 234028,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893081.319, "dur": 0.764, + "args": { + "External id": 234029,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893083.249, "dur": 0.947, + "args": { + "External id": 234030,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893088.033, "dur": 0.746, + "args": { + "External id": 234031,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893089.432, "dur": 0.845, + "args": { + "External id": 234032,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893091.406, "dur": 6.233, + "args": { + "External id": 234033,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115893110.783, "dur": 29.804, + "args": { + "External id": 234034,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 4145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115893169.091, "dur": 87.776, + "args": { + "External id": 234035,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 4146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115893177.922, "dur": 3.141, + "args": { + "External id": 234036,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115893185.869, "dur": 9.807, + "args": { + "External id": 234037,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 4148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115893189.905, "dur": 5.396, + "args": { + "External id": 234038,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 4149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893193.228, "dur": 0.617, + "args": { + "External id": 234039,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 4150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115893203.979, "dur": 19.783, + "args": { + "External id": 234040,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 4151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893205.442, "dur": 0.873, + "args": { + "External id": 234041,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893207.633, "dur": 0.414, + "args": { + "External id": 234042,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893209.156, "dur": 0.602, + "args": { + "External id": 234043,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893210.847, "dur": 1.016, + "args": { + "External id": 234044,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893212.957, "dur": 0.650, + "args": { + "External id": 234045,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893214.836, "dur": 0.530, + "args": { + "External id": 234046,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893216.902, "dur": 0.519, + "args": { + "External id": 234047,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893218.351, "dur": 0.605, + "args": { + "External id": 234048,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115893219.995, "dur": 0.594, + "args": { + "External id": 234049,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115893232.345, "dur": 17.213, + "args": { + "External id": 234050,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 4161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115893296.359, "dur": 107.853, + "args": { + "External id": 234051,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 4162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115893318.816, "dur": 81.922, + "args": { + "External id": 234052,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4163, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115893327.950, "dur": 68.687, + "args": { + "External id": 234053,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 4164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115893417.786, "dur": 2.021, + "args": { + "External id": 234054,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4165, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115893510.892, "dur": 1528.270, + "args": { + "External id": 234055,"Sequence number": 2757750, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 4166 + } + }, + { + "ph": "f", "id": 206, "pid": 4183440, "tid": 31337, "ts": 667115893510.892, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115893622.915, "dur": 136.565, + "args": { + "External id": 234056,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 4167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115893803.352, "dur": 36.374, + "args": { + "External id": 234057,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 4168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115893856.747, "dur": 41.205, + "args": { + "External id": 234058,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 4169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115893908.644, "dur": 24.969, + "args": { + "External id": 234059,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 4170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115893940.094, "dur": 31.836, + "args": { + "External id": 234060,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 4171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115893978.778, "dur": 20.273, + "args": { + "External id": 234061,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 4172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115894006.482, "dur": 27.765, + "args": { + "External id": 234062,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 4173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115894056.744, "dur": 21.291, + "args": { + "External id": 234063,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 4174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115894103.452, "dur": 25.918, + "args": { + "External id": 234064,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115894147.521, "dur": 17.925, + "args": { + "External id": 234065,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 4176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115894177.181, "dur": 13.662, + "args": { + "External id": 234066,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 4177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115894198.487, "dur": 35.521, + "args": { + "External id": 234067,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 4178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115894237.313, "dur": 30.027, + "args": { + "External id": 234068,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115894291.425, "dur": 159.919, + "args": { + "External id": 234069,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115894362.239, "dur": 5.683, + "args": { + "External id": 234070,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115894369.839, "dur": 2.732, + "args": { + "External id": 234071,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115894480.520, "dur": 41.511, + "args": { + "External id": 234072,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115894535.352, "dur": 16.381, + "args": { + "External id": 234073,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115894560.886, "dur": 46.458, + "args": { + "External id": 234074,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 4185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115894613.357, "dur": 30.999, + "args": { + "External id": 234075,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115894683.737, "dur": 33.859, + "args": { + "External id": 234076,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 4187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115894724.828, "dur": 28.242, + "args": { + "External id": 234077,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115894759.490, "dur": 25.583, + "args": { + "External id": 234078,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 4189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115894792.223, "dur": 27.328, + "args": { + "External id": 234079,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115894838.792, "dur": 20.204, + "args": { + "External id": 234080,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 4191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115894875.379, "dur": 21.978, + "args": { + "External id": 234081,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115894912.555, "dur": 31.060, + "args": { + "External id": 234082,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 4193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115894968.032, "dur": 12.824, + "args": { + "External id": 234083,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 4194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115894993.431, "dur": 15.458, + "args": { + "External id": 234084,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 4195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115895082.267, "dur": 15.232, + "args": { + "External id": 234085,"Record function id": 0, "Ev Idx": 4196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115895085.264, "dur": 11.310, + "args": { + "External id": 234086,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115895089.793, "dur": 6.015, + "args": { + "External id": 234087,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115895091.289, "dur": 4.419, + "args": { + "External id": 234088,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115895101.147, "dur": 4.661, + "args": { + "External id": 234089,"Record function id": 0, "Ev Idx": 4200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115895102.486, "dur": 2.857, + "args": { + "External id": 234090,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115895103.166, "dur": 1.712, + "args": { + "External id": 234091,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115895103.815, "dur": 0.969, + "args": { + "External id": 234092,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115895108.981, "dur": 4.470, + "args": { + "External id": 234093,"Record function id": 0, "Ev Idx": 4204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115895110.004, "dur": 3.041, + "args": { + "External id": 234094,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115895110.626, "dur": 2.021, + "args": { + "External id": 234095,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115895111.309, "dur": 1.276, + "args": { + "External id": 234096,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115895116.616, "dur": 4.021, + "args": { + "External id": 234097,"Record function id": 0, "Ev Idx": 4208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115895117.848, "dur": 2.386, + "args": { + "External id": 234098,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 4209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115895118.367, "dur": 1.481, + "args": { + "External id": 234099,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 4210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115895118.856, "dur": 0.898, + "args": { + "External id": 234100,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 4211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115895123.722, "dur": 4.105, + "args": { + "External id": 234101,"Record function id": 0, "Ev Idx": 4212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115895124.807, "dur": 2.576, + "args": { + "External id": 234102,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115895125.406, "dur": 1.575, + "args": { + "External id": 234103,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115895125.924, "dur": 0.964, + "args": { + "External id": 234104,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115895133.960, "dur": 4.676, + "args": { + "External id": 234105,"Record function id": 0, "Ev Idx": 4216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115895135.274, "dur": 2.934, + "args": { + "External id": 234106,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115895135.851, "dur": 1.996, + "args": { + "External id": 234107,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115895136.683, "dur": 1.063, + "args": { + "External id": 234108,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115895141.822, "dur": 4.520, + "args": { + "External id": 234109,"Record function id": 0, "Ev Idx": 4220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115895142.876, "dur": 3.058, + "args": { + "External id": 234110,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115895143.455, "dur": 2.092, + "args": { + "External id": 234111,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115895144.271, "dur": 1.170, + "args": { + "External id": 234112,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115895149.328, "dur": 3.997, + "args": { + "External id": 234113,"Record function id": 0, "Ev Idx": 4224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115895150.327, "dur": 2.573, + "args": { + "External id": 234114,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115895150.816, "dur": 1.679, + "args": { + "External id": 234115,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115895151.499, "dur": 0.893, + "args": { + "External id": 234116,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115895156.842, "dur": 3.811, + "args": { + "External id": 234117,"Record function id": 0, "Ev Idx": 4228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115895157.779, "dur": 2.457, + "args": { + "External id": 234118,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115895158.225, "dur": 1.627, + "args": { + "External id": 234119,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115895158.982, "dur": 0.764, + "args": { + "External id": 234120,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115895164.396, "dur": 15126.268, + "args": { + "External id": 234121,"Record function id": 0, "Sequence number": 2757749, "Fwd thread id": 1, "Ev Idx": 4232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115895165.585, "dur": 15116.953, + "args": { + "External id": 234122,"Sequence number": 2757749, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 4233 + } + }, + { + "ph": "f", "id": 207, "pid": 4183440, "tid": 31337, "ts": 667115895165.585, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.2)", "pid": 4183440, "tid": 31337, + "ts": 667115895193.439, "dur": 34.538, + "args": { + "External id": 234123,"Record function id": 0, "Ev Idx": 4234 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.2)", "pid": 4183440, "tid": 31337, + "ts": 667115895235.391, "dur": 60.597, + "args": { + "External id": 234124,"Record function id": 0, "Ev Idx": 4235 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.2)", "pid": 4183440, "tid": 31337, + "ts": 667115895302.281, "dur": 14972.949, + "args": { + "External id": 234125,"Record function id": 0, "Ev Idx": 4236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115895386.494, "dur": 6.419, + "args": { + "External id": 234126,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115895401.894, "dur": 4.525, + "args": { + "External id": 234127,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 4238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115895423.560, "dur": 14146.957, + "args": { + "External id": 234128,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 4239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115895436.496, "dur": 14125.990, + "args": { + "External id": 234129,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 4240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115895462.258, "dur": 13.197, + "args": { + "External id": 234130,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115895483.174, "dur": 14045.337, + "args": { + "External id": 234131,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 4242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115895485.259, "dur": 14042.394, + "args": { + "External id": 234132,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 4243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115895488.827, "dur": 24.595, + "args": { + "External id": 234133,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115895516.109, "dur": 14007.966, + "args": { + "External id": 234134,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 4245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115909684.328, "dur": 10.396, + "args": { + "External id": 234135,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 4246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115909687.209, "dur": 6.937, + "args": { + "External id": 234136,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115909721.617, "dur": 290.408, + "args": { + "External id": 234137,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 4248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115909745.828, "dur": 261.524, + "args": { + "External id": 234138,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4249, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115909758.656, "dur": 243.680, + "args": { + "External id": 234139,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 4250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115910027.048, "dur": 2.186, + "args": { + "External id": 234140,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4251, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910081.843, "dur": 5.993, + "args": { + "External id": 234141,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910132.223, "dur": 1.299, + "args": { + "External id": 234142,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910147.269, "dur": 1.370, + "args": { + "External id": 234143,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910159.020, "dur": 1.016, + "args": { + "External id": 234144,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910170.671, "dur": 1.022, + "args": { + "External id": 234145,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910181.696, "dur": 1.104, + "args": { + "External id": 234146,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910193.243, "dur": 1.322, + "args": { + "External id": 234147,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910205.230, "dur": 0.949, + "args": { + "External id": 234148,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910215.291, "dur": 1.292, + "args": { + "External id": 234149,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115910303.164, "dur": 2609.370, + "args": { + "External id": 234150,"Record function id": 0, "Ev Idx": 4261 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.1)", "pid": 4183440, "tid": 31337, + "ts": 667115910322.004, "dur": 969.003, + "args": { + "External id": 234151,"Record function id": 0, "Ev Idx": 4262 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 4183440, "tid": 31337, + "ts": 667115910336.915, "dur": 312.731, + "args": { + "External id": 234152,"Record function id": 0, "Ev Idx": 4263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115910413.588, "dur": 4.059, + "args": { + "External id": 234153,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 4264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115910421.127, "dur": 1.128, + "args": { + "External id": 234154,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115910424.163, "dur": 0.873, + "args": { + "External id": 234155,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115910426.843, "dur": 0.917, + "args": { + "External id": 234156,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115910429.492, "dur": 0.974, + "args": { + "External id": 234157,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115910432.364, "dur": 1.157, + "args": { + "External id": 234158,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115910435.059, "dur": 1.067, + "args": { + "External id": 234159,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115910437.670, "dur": 1.336, + "args": { + "External id": 234160,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115910440.999, "dur": 0.983, + "args": { + "External id": 234161,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115910443.534, "dur": 0.966, + "args": { + "External id": 234162,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115910461.278, "dur": 156.814, + "args": { + "External id": 234163,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 4274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115910477.527, "dur": 136.296, + "args": { + "External id": 234164,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 4275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115910489.387, "dur": 31.816, + "args": { + "External id": 234165,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115910525.178, "dur": 62.902, + "args": { + "External id": 234166,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 4277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115910528.928, "dur": 58.803, + "args": { + "External id": 234167,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 4278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910532.745, "dur": 6.150, + "args": { + "External id": 234168,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115910541.718, "dur": 45.380, + "args": { + "External id": 234169,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 4280 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.0", "pid": 4183440, "tid": 31337, + "ts": 667115910774.526, "dur": 509.623, + "args": { + "External id": 234170,"Record function id": 0, "Ev Idx": 4281 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 4183440, "tid": 31337, + "ts": 667115910792.116, "dur": 480.378, + "args": { + "External id": 234171,"Record function id": 0, "Ev Idx": 4282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115910852.726, "dur": 6.359, + "args": { + "External id": 234172,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115910875.090, "dur": 28.219, + "args": { + "External id": 234173,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 4284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910879.592, "dur": 1.789, + "args": { + "External id": 234174,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910884.625, "dur": 0.808, + "args": { + "External id": 234175,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910886.585, "dur": 0.480, + "args": { + "External id": 234176,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910888.303, "dur": 0.599, + "args": { + "External id": 234177,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910891.510, "dur": 0.832, + "args": { + "External id": 234178,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910893.508, "dur": 0.510, + "args": { + "External id": 234179,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910895.245, "dur": 1.015, + "args": { + "External id": 234180,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910897.433, "dur": 0.610, + "args": { + "External id": 234181,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115910899.102, "dur": 0.611, + "args": { + "External id": 234182,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115910913.745, "dur": 30.819, + "args": { + "External id": 234183,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 4294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 31337, + "ts": 667115910975.528, "dur": 91.742, + "args": { + "External id": 234184,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 4295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115910985.457, "dur": 3.514, + "args": { + "External id": 234185,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 31337, + "ts": 667115910993.383, "dur": 9.575, + "args": { + "External id": 234186,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 4297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 31337, + "ts": 667115910997.393, "dur": 5.147, + "args": { + "External id": 234187,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 4298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115911000.627, "dur": 0.667, + "args": { + "External id": 234188,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 4299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 31337, + "ts": 667115911009.606, "dur": 23.012, + "args": { + "External id": 234189,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 4300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115911011.410, "dur": 1.512, + "args": { + "External id": 234190,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115911014.191, "dur": 0.581, + "args": { + "External id": 234191,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115911015.873, "dur": 0.726, + "args": { + "External id": 234192,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115911018.842, "dur": 0.469, + "args": { + "External id": 234193,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115911020.498, "dur": 0.637, + "args": { + "External id": 234194,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115911022.288, "dur": 0.544, + "args": { + "External id": 234195,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115911023.904, "dur": 0.708, + "args": { + "External id": 234196,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115911025.672, "dur": 0.748, + "args": { + "External id": 234197,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115911027.661, "dur": 1.027, + "args": { + "External id": 234198,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 31337, + "ts": 667115911042.548, "dur": 17.495, + "args": { + "External id": 234199,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 4310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 31337, + "ts": 667115911108.037, "dur": 104.439, + "args": { + "External id": 234200,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 4311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115911129.477, "dur": 79.631, + "args": { + "External id": 234201,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4312, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 31337, + "ts": 667115911138.638, "dur": 66.357, + "args": { + "External id": 234202,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 4313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115911224.781, "dur": 1.555, + "args": { + "External id": 234203,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4314, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115911298.564, "dur": 1589.444, + "args": { + "External id": 234204,"Sequence number": 2757748, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 4315 + } + }, + { + "ph": "f", "id": 208, "pid": 4183440, "tid": 31337, "ts": 667115911298.564, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115911406.424, "dur": 116.388, + "args": { + "External id": 234205,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 4316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115911565.049, "dur": 37.362, + "args": { + "External id": 234206,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 4317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115911620.131, "dur": 84.731, + "args": { + "External id": 234207,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 4318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115911719.794, "dur": 31.641, + "args": { + "External id": 234208,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 4319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115911758.158, "dur": 34.815, + "args": { + "External id": 234209,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 4320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115911799.829, "dur": 20.968, + "args": { + "External id": 234210,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 4321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115911828.750, "dur": 29.580, + "args": { + "External id": 234211,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 4322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115911882.598, "dur": 24.760, + "args": { + "External id": 234212,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 4323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115911924.026, "dur": 28.876, + "args": { + "External id": 234213,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115911972.109, "dur": 19.145, + "args": { + "External id": 234214,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 4325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115912004.210, "dur": 15.777, + "args": { + "External id": 234215,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 4326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115912028.394, "dur": 35.297, + "args": { + "External id": 234216,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 4327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115912066.957, "dur": 30.203, + "args": { + "External id": 234217,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115912123.270, "dur": 163.343, + "args": { + "External id": 234218,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115912197.987, "dur": 5.894, + "args": { + "External id": 234219,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115912205.645, "dur": 3.159, + "args": { + "External id": 234220,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115912317.223, "dur": 24.621, + "args": { + "External id": 234221,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115912353.784, "dur": 15.345, + "args": { + "External id": 234222,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115912376.458, "dur": 42.766, + "args": { + "External id": 234223,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 4334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115912425.291, "dur": 30.804, + "args": { + "External id": 234224,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115912462.819, "dur": 27.194, + "args": { + "External id": 234225,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 4336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115912514.808, "dur": 33.560, + "args": { + "External id": 234226,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115912555.188, "dur": 26.157, + "args": { + "External id": 234227,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 4338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115912589.665, "dur": 28.208, + "args": { + "External id": 234228,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115912634.757, "dur": 57.011, + "args": { + "External id": 234229,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 4340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115912714.308, "dur": 35.908, + "args": { + "External id": 234230,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115912772.740, "dur": 20.189, + "args": { + "External id": 234231,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 4342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115912809.522, "dur": 14.921, + "args": { + "External id": 234232,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 4343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115912836.401, "dur": 21.859, + "args": { + "External id": 234233,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 4344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115912933.781, "dur": 14.837, + "args": { + "External id": 234234,"Record function id": 0, "Ev Idx": 4345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115912936.959, "dur": 10.636, + "args": { + "External id": 234235,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115912941.127, "dur": 5.677, + "args": { + "External id": 234236,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115912942.681, "dur": 4.038, + "args": { + "External id": 234237,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115912952.482, "dur": 5.034, + "args": { + "External id": 234238,"Record function id": 0, "Ev Idx": 4349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115912954.022, "dur": 3.052, + "args": { + "External id": 234239,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115912954.707, "dur": 1.832, + "args": { + "External id": 234240,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115912955.381, "dur": 1.068, + "args": { + "External id": 234241,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115912960.781, "dur": 4.413, + "args": { + "External id": 234242,"Record function id": 0, "Ev Idx": 4353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115912962.228, "dur": 2.553, + "args": { + "External id": 234243,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115912962.723, "dur": 1.669, + "args": { + "External id": 234244,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115912963.236, "dur": 1.043, + "args": { + "External id": 234245,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115912968.342, "dur": 4.110, + "args": { + "External id": 234246,"Record function id": 0, "Ev Idx": 4357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115912969.543, "dur": 2.506, + "args": { + "External id": 234247,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 4358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115912970.186, "dur": 1.477, + "args": { + "External id": 234248,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 4359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115912970.849, "dur": 0.702, + "args": { + "External id": 234249,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 4360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115912975.494, "dur": 4.185, + "args": { + "External id": 234250,"Record function id": 0, "Ev Idx": 4361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115912976.798, "dur": 2.443, + "args": { + "External id": 234251,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115912977.248, "dur": 1.570, + "args": { + "External id": 234252,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115912977.797, "dur": 0.900, + "args": { + "External id": 234253,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115912982.674, "dur": 3.669, + "args": { + "External id": 234254,"Record function id": 0, "Ev Idx": 4365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115912983.836, "dur": 2.098, + "args": { + "External id": 234255,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115912984.296, "dur": 1.159, + "args": { + "External id": 234256,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115912984.608, "dur": 0.737, + "args": { + "External id": 234257,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115912989.614, "dur": 3.789, + "args": { + "External id": 234258,"Record function id": 0, "Ev Idx": 4369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115912991.054, "dur": 1.945, + "args": { + "External id": 234259,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115912991.564, "dur": 1.036, + "args": { + "External id": 234260,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115912991.828, "dur": 0.668, + "args": { + "External id": 234261,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115912996.364, "dur": 3.657, + "args": { + "External id": 234262,"Record function id": 0, "Ev Idx": 4373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115912997.496, "dur": 2.107, + "args": { + "External id": 234263,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115912997.935, "dur": 1.266, + "args": { + "External id": 234264,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115912998.276, "dur": 0.810, + "args": { + "External id": 234265,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115913003.328, "dur": 3.862, + "args": { + "External id": 234266,"Record function id": 0, "Ev Idx": 4377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115913004.459, "dur": 2.298, + "args": { + "External id": 234267,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115913004.927, "dur": 1.355, + "args": { + "External id": 234268,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115913005.301, "dur": 0.885, + "args": { + "External id": 234269,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115913011.383, "dur": 15167.886, + "args": { + "External id": 234270,"Record function id": 0, "Sequence number": 2757747, "Fwd thread id": 1, "Ev Idx": 4381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115913012.386, "dur": 15159.279, + "args": { + "External id": 234271,"Sequence number": 2757747, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 4382 + } + }, + { + "ph": "f", "id": 209, "pid": 4183440, "tid": 31337, "ts": 667115913012.386, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.1)", "pid": 4183440, "tid": 31337, + "ts": 667115913039.544, "dur": 37.672, + "args": { + "External id": 234272,"Record function id": 0, "Ev Idx": 4383 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.1)", "pid": 4183440, "tid": 31337, + "ts": 667115913084.575, "dur": 66.158, + "args": { + "External id": 234273,"Record function id": 0, "Ev Idx": 4384 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.1)", "pid": 4183440, "tid": 31337, + "ts": 667115913159.660, "dur": 15004.855, + "args": { + "External id": 234274,"Record function id": 0, "Ev Idx": 4385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115913244.062, "dur": 6.353, + "args": { + "External id": 234275,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115913259.307, "dur": 4.805, + "args": { + "External id": 234276,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 4387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115913277.857, "dur": 13904.332, + "args": { + "External id": 234277,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 4388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115913290.586, "dur": 13883.505, + "args": { + "External id": 234278,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 4389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115913315.588, "dur": 13.873, + "args": { + "External id": 234279,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115913333.645, "dur": 13805.967, + "args": { + "External id": 234280,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 4391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115913336.432, "dur": 13802.466, + "args": { + "External id": 234281,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 4392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115913340.290, "dur": 4.787, + "args": { + "External id": 234282,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115913346.744, "dur": 13788.500, + "args": { + "External id": 234283,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 4394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115927267.699, "dur": 9.579, + "args": { + "External id": 234284,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 4395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115927270.567, "dur": 6.362, + "args": { + "External id": 234285,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115927302.902, "dur": 575.195, + "args": { + "External id": 234286,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 4397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115927327.191, "dur": 544.589, + "args": { + "External id": 234287,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4398, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115927338.004, "dur": 527.292, + "args": { + "External id": 234288,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 4399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115927902.598, "dur": 2.581, + "args": { + "External id": 234289,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4400, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115927970.257, "dur": 7.091, + "args": { + "External id": 234290,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115928020.126, "dur": 1.485, + "args": { + "External id": 234291,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115928036.079, "dur": 1.216, + "args": { + "External id": 234292,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115928048.561, "dur": 1.059, + "args": { + "External id": 234293,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115928061.595, "dur": 1.081, + "args": { + "External id": 234294,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115928072.085, "dur": 1.128, + "args": { + "External id": 234295,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115928084.278, "dur": 1.019, + "args": { + "External id": 234296,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115928095.443, "dur": 1.132, + "args": { + "External id": 234297,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115928105.895, "dur": 1.073, + "args": { + "External id": 234298,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115928192.529, "dur": 1965.168, + "args": { + "External id": 234299,"Record function id": 0, "Ev Idx": 4410 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.0)", "pid": 4183440, "tid": 31337, + "ts": 667115928211.639, "dur": 423.479, + "args": { + "External id": 234300,"Record function id": 0, "Ev Idx": 4411 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 4183440, "tid": 31337, + "ts": 667115928227.861, "dur": 311.766, + "args": { + "External id": 234301,"Record function id": 0, "Ev Idx": 4412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115928309.720, "dur": 4.162, + "args": { + "External id": 234302,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 4413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115928317.853, "dur": 1.018, + "args": { + "External id": 234303,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115928320.665, "dur": 1.059, + "args": { + "External id": 234304,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115928323.752, "dur": 0.947, + "args": { + "External id": 234305,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115928326.812, "dur": 1.366, + "args": { + "External id": 234306,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115928329.861, "dur": 1.043, + "args": { + "External id": 234307,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115928332.158, "dur": 0.972, + "args": { + "External id": 234308,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115928334.904, "dur": 1.079, + "args": { + "External id": 234309,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115928337.468, "dur": 1.191, + "args": { + "External id": 234310,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115928340.255, "dur": 0.976, + "args": { + "External id": 234311,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115928358.488, "dur": 132.607, + "args": { + "External id": 234312,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 4423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 31337, + "ts": 667115928374.068, "dur": 113.068, + "args": { + "External id": 234313,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 4424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115928385.779, "dur": 12.988, + "args": { + "External id": 234314,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115928401.375, "dur": 59.726, + "args": { + "External id": 234315,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 4426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115928403.613, "dur": 57.187, + "args": { + "External id": 234316,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 4427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115928407.663, "dur": 6.832, + "args": { + "External id": 234317,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115928416.147, "dur": 43.798, + "args": { + "External id": 234318,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 4429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115928642.037, "dur": 1495.180, + "args": { + "External id": 234319,"Sequence number": 2757746, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 4430 + } + }, + { + "ph": "f", "id": 210, "pid": 4183440, "tid": 31337, "ts": 667115928642.037, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115928787.072, "dur": 100.415, + "args": { + "External id": 234320,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [2816, 1], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 4431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 4183440, "tid": 31337, + "ts": 667115928926.020, "dur": 36.748, + "args": { + "External id": 234321,"kernel_hash": "clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/lk/clkmb2nvivik7xt77lza2snvzeuraclmpbqhk34lgigbl7zlxati.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [65536, 2816], [16, 4096, 2816], [16, 4096, 2816], [16, 4096, 2816], []], "Ev Idx": 4432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 4183440, "tid": 31337, + "ts": 667115928978.827, "dur": 39.542, + "args": { + "External id": 234322,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 1024], [0, 2816, 1], [2883584, 2816, 1]], "Input Dims": [[1, 1024, 65536], [1, 65536, 2816], [1, 1024, 2816]], "Ev Idx": 4433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115929027.313, "dur": 26.342, + "args": { + "External id": 234323,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 4434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115929060.419, "dur": 32.976, + "args": { + "External id": 234324,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 4435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115929100.462, "dur": 21.287, + "args": { + "External id": 234325,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2816], [1024, 1], [1024, 1]], "Input Dims": [[2816, 65536], [65536, 1024], [2816, 1024]], "Ev Idx": 4436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115929130.068, "dur": 29.302, + "args": { + "External id": 234326,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 4437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 4183440, "tid": 31337, + "ts": 667115929180.174, "dur": 21.218, + "args": { + "External id": 234327,"kernel_hash": "cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/md/cmdhmofoq6dkjtzh34c2kzhgghtmhpal5f3rxqvpfiur2wxglwjs.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 4438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 4183440, "tid": 31337, + "ts": 667115929218.251, "dur": 27.601, + "args": { + "External id": 234328,"kernel_hash": "cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ue/cuevaar5u646bgtmpubrbyzqz3sdut3cwthdo7wpizzjr6oluqi5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115929263.409, "dur": 18.144, + "args": { + "External id": 234329,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 4440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115929292.243, "dur": 14.774, + "args": { + "External id": 234330,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 4441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115929315.847, "dur": 32.989, + "args": { + "External id": 234331,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 4442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115929351.996, "dur": 29.703, + "args": { + "External id": 234332,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 4183440, "tid": 31337, + "ts": 667115929407.042, "dur": 181.940, + "args": { + "External id": 234333,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [65536, 4096, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 16, 4096], [16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115929475.426, "dur": 6.086, + "args": { + "External id": 234334,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115929483.347, "dur": 2.725, + "args": { + "External id": 234335,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115929621.586, "dur": 24.050, + "args": { + "External id": 234336,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 31337, + "ts": 667115929692.414, "dur": 18.512, + "args": { + "External id": 234337,"kernel_hash": "cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/nn/cnnjyph67nk54fjnuktc2nmchkiw5uvx4mqovnyasu7ursptxrg7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115929721.672, "dur": 50.866, + "args": { + "External id": 234338,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 4449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115929778.631, "dur": 31.142, + "args": { + "External id": 234339,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115929816.250, "dur": 26.442, + "args": { + "External id": 234340,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 4451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115929848.047, "dur": 27.531, + "args": { + "External id": 234341,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115929880.928, "dur": 26.559, + "args": { + "External id": 234342,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [1024, 1], [1024, 1]], "Input Dims": [[1024, 65536], [65536, 1024], [1024, 1024]], "Ev Idx": 4453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 31337, + "ts": 667115929915.277, "dur": 28.380, + "args": { + "External id": 234343,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 4183440, "tid": 31337, + "ts": 667115929959.722, "dur": 21.512, + "args": { + "External id": 234344,"kernel_hash": "cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/n6/cn6a6cq4k7qdw3wki5ksil45pjzcbfrfjarshv63ivxttjehkezz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [65536, 1024], []], "Ev Idx": 4455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 4183440, "tid": 31337, + "ts": 667115929997.681, "dur": 23.233, + "args": { + "External id": 234345,"kernel_hash": "cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "1024", "1", "497", "132", "True", "1024", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/wv/cwvn5v4u6cexxzo6wfnjojuuby7ad6wk6jmjnzhsan4mprdashfg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [1024], [65536, 1024], [65536, 1024], [132, 1024], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 4183440, "tid": 31337, + "ts": 667115930035.183, "dur": 16.073, + "args": { + "External id": 234346,"kernel_hash": "cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "66"], "kernel_file": "/tmp/torchinductor_cvm/w4/cw4ogu6mqrgcawgfqkyrzhc5xil4j4vfrn34wqhb2qfx2hbqyotj.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [2048, 1, 1024], [], []], "Input Dims": [[132, 1024], [1, 1024, 2], [], []], "Ev Idx": 4457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 4183440, "tid": 31337, + "ts": 667115930065.260, "dur": 15.310, + "args": { + "External id": 234347,"kernel_hash": "c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao", "grid": "grid(1024,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "1024", "2"], "kernel_file": "/tmp/torchinductor_cvm/3d/c3dzxlwq2gbpkrmfvuijgv5eon5iwfw455hggookxniqczni5xao.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1, 1024], [1024, 1], [], []], "Input Dims": [[1, 1024, 2], [1, 1024], [], []], "Ev Idx": 4458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 4183440, "tid": 31337, + "ts": 667115930092.068, "dur": 15.608, + "args": { + "External id": 234348,"kernel_hash": "cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/x5/cx5ypd3rju7i5obvafc2itek3ewywgqdgrrndct7omk4mswsdop7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], [16, 4096, 1024], []], "Ev Idx": 4459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115930178.746, "dur": 15.975, + "args": { + "External id": 234349,"Record function id": 0, "Ev Idx": 4460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115930182.126, "dur": 11.592, + "args": { + "External id": 234350,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115930186.286, "dur": 6.615, + "args": { + "External id": 234351,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115930187.795, "dur": 5.006, + "args": { + "External id": 234352,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115930198.599, "dur": 4.666, + "args": { + "External id": 234353,"Record function id": 0, "Ev Idx": 4464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115930200.154, "dur": 2.643, + "args": { + "External id": 234354,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115930200.886, "dur": 1.468, + "args": { + "External id": 234355,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115930201.285, "dur": 1.004, + "args": { + "External id": 234356,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115930206.446, "dur": 4.985, + "args": { + "External id": 234357,"Record function id": 0, "Ev Idx": 4468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115930208.074, "dur": 2.910, + "args": { + "External id": 234358,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115930208.675, "dur": 1.889, + "args": { + "External id": 234359,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115930209.312, "dur": 1.179, + "args": { + "External id": 234360,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1024]], "Ev Idx": 4471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115930214.649, "dur": 4.217, + "args": { + "External id": 234361,"Record function id": 0, "Ev Idx": 4472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115930216.167, "dur": 2.270, + "args": { + "External id": 234362,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 4473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115930216.706, "dur": 1.306, + "args": { + "External id": 234363,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 4474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115930217.182, "dur": 0.753, + "args": { + "External id": 234364,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 4475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115930222.029, "dur": 4.895, + "args": { + "External id": 234365,"Record function id": 0, "Ev Idx": 4476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115930223.419, "dur": 3.065, + "args": { + "External id": 234366,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115930224.213, "dur": 1.733, + "args": { + "External id": 234367,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115930224.731, "dur": 1.130, + "args": { + "External id": 234368,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115930229.999, "dur": 4.686, + "args": { + "External id": 234369,"Record function id": 0, "Ev Idx": 4480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115930231.502, "dur": 2.711, + "args": { + "External id": 234370,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115930232.008, "dur": 1.802, + "args": { + "External id": 234371,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115930232.637, "dur": 1.108, + "args": { + "External id": 234372,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115930237.929, "dur": 3.963, + "args": { + "External id": 234373,"Record function id": 0, "Ev Idx": 4484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115930239.171, "dur": 2.283, + "args": { + "External id": 234374,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115930239.670, "dur": 1.399, + "args": { + "External id": 234375,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115930240.117, "dur": 0.873, + "args": { + "External id": 234376,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115930245.140, "dur": 4.021, + "args": { + "External id": 234377,"Record function id": 0, "Ev Idx": 4488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115930246.297, "dur": 2.426, + "args": { + "External id": 234378,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115930247.034, "dur": 1.283, + "args": { + "External id": 234379,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115930247.319, "dur": 0.936, + "args": { + "External id": 234380,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 4491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115930252.360, "dur": 4.644, + "args": { + "External id": 234381,"Record function id": 0, "Ev Idx": 4492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115930253.998, "dur": 2.552, + "args": { + "External id": 234382,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115930254.879, "dur": 1.250, + "args": { + "External id": 234383,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115930255.256, "dur": 0.807, + "args": { + "External id": 234384,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 4495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115930260.549, "dur": 15673.516, + "args": { + "External id": 234385,"Record function id": 0, "Sequence number": 2757745, "Fwd thread id": 1, "Ev Idx": 4496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115930261.679, "dur": 15664.295, + "args": { + "External id": 234386,"Sequence number": 2757745, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 4497 + } + }, + { + "ph": "f", "id": 211, "pid": 4183440, "tid": 31337, "ts": 667115930261.679, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.0)", "pid": 4183440, "tid": 31337, + "ts": 667115930289.306, "dur": 38.840, + "args": { + "External id": 234387,"Record function id": 0, "Ev Idx": 4498 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.0)", "pid": 4183440, "tid": 31337, + "ts": 667115930335.703, "dur": 69.697, + "args": { + "External id": 234388,"Record function id": 0, "Ev Idx": 4499 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.0)", "pid": 4183440, "tid": 31337, + "ts": 667115930411.390, "dur": 15506.363, + "args": { + "External id": 234389,"Record function id": 0, "Ev Idx": 4500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115930516.900, "dur": 7.513, + "args": { + "External id": 234390,"Record function id": 0, "Concrete Inputs": ["[12847104]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115930535.086, "dur": 5.492, + "args": { + "External id": 234391,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 4502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115930555.109, "dur": 14673.208, + "args": { + "External id": 234392,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 4503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115930568.307, "dur": 14651.870, + "args": { + "External id": 234393,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [1024, 1], [1024, 1], [1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], [], [], [1605888, 1]], "Input Dims": [[[1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], [], [], [8, 1605888]], "Ev Idx": 4504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115930591.207, "dur": 13.962, + "args": { + "External id": 234394,"Record function id": 0, "Concrete Inputs": ["[3194]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115930619.226, "dur": 14556.961, + "args": { + "External id": 234395,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], [], []], "Ev Idx": 4506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115930621.710, "dur": 14553.767, + "args": { + "External id": 234396,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3194], [], [], [], [], [], []], "Ev Idx": 4507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115930626.281, "dur": 7.903, + "args": { + "External id": 234397,"Record function id": 0, "Concrete Inputs": ["[3194]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115930636.521, "dur": 14536.728, + "args": { + "External id": 234398,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3194], [3194], []], "Ev Idx": 4509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115945314.204, "dur": 8.989, + "args": { + "External id": 234399,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[12847104], [], [], [], [], []], "Ev Idx": 4510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115945316.987, "dur": 5.803, + "args": { + "External id": 234400,"Record function id": 0, "Concrete Inputs": ["[1605888]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115945350.012, "dur": 260.398, + "args": { + "External id": 234401,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[1605888], [12847104], [], [], [], []], "Ev Idx": 4512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115945375.006, "dur": 230.426, + "args": { + "External id": 234402,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1605888, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[12847104], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4513, "In msg nelems": 12847104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115945386.389, "dur": 213.723, + "args": { + "External id": 234403,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[12847104]], "Ev Idx": 4514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115945628.278, "dur": 2.091, + "args": { + "External id": 234404,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4515, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115945717.500, "dur": 6.514, + "args": { + "External id": 234405,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115945767.740, "dur": 1.362, + "args": { + "External id": 234406,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115945784.780, "dur": 1.519, + "args": { + "External id": 234407,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "131200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115945797.637, "dur": 1.257, + "args": { + "External id": 234408,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "262272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115945809.842, "dur": 1.133, + "args": { + "External id": 234409,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "393344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115945822.430, "dur": 1.382, + "args": { + "External id": 234410,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115945834.066, "dur": 1.084, + "args": { + "External id": 234411,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115945846.857, "dur": 1.068, + "args": { + "External id": 234412,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "884992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115945857.420, "dur": 0.756, + "args": { + "External id": 234413,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "1245440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115945948.972, "dur": 259.518, + "args": { + "External id": 234414,"Record function id": 0, "Sequence number": 2757744, "Fwd thread id": 1, "Ev Idx": 4525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 4183440, "tid": 31337, + "ts": 667115945951.677, "dur": 249.632, + "args": { + "External id": 234415,"Sequence number": 2757744, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 4526 + } + }, + { + "ph": "f", "id": 212, "pid": 4183440, "tid": 31337, "ts": 667115945951.677, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_0", "pid": 4183440, "tid": 31337, + "ts": 667115946065.519, "dur": 44.547, + "args": { + "External id": 234416,"kernel_hash": "c7lrjviqywzcm5hk2t7vdx7xifw6stkqur6fe7dmvpxac6sz5vlo", "grid": "grid(32768000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "32768000"], "kernel_file": "/tmp/torchinductor_cvm/7l/c7lrjviqywzcm5hk2t7vdx7xifw6stkqur6fe7dmvpxac6sz5vlo.py", "kernel_backend": "triton", "Input type": ["float", "Scalar"], "Input Strides": [[1024, 1], []], "Input Dims": [[32000, 1024], []], "Ev Idx": 4527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_1", "pid": 4183440, "tid": 31337, + "ts": 667115946123.927, "dur": 27.645, + "args": { + "External id": 234417,"kernel_hash": "cscjidpvuk343sjfekiiiiwri6lwsclxtrh5mtw6qkxwruob6l4f", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/sc/cscjidpvuk343sjfekiiiiwri6lwsclxtrh5mtw6qkxwruob6l4f.py", "kernel_backend": "triton", "Input type": ["long int", "c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096], [16, 4096, 1024], [32000, 1024], []], "Ev Idx": 4528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_2", "pid": 4183440, "tid": 31337, + "ts": 667115946167.210, "dur": 19.302, + "args": { + "External id": 234418,"kernel_hash": "c3bfwa4cit2k7w2i4shgk24meojhbvgxgmbsw6tpqtobrl2y6ht2", "grid": "grid(32768000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "32768000"], "kernel_file": "/tmp/torchinductor_cvm/3b/c3bfwa4cit2k7w2i4shgk24meojhbvgxgmbsw6tpqtobrl2y6ht2.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 4529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115946217.803, "dur": 14.499, + "args": { + "External id": 234419,"Record function id": 0, "Ev Idx": 4530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 4183440, "tid": 31337, + "ts": 667115946220.990, "dur": 10.491, + "args": { + "External id": 234420,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 4531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 31337, + "ts": 667115946224.844, "dur": 5.814, + "args": { + "External id": 234421,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 4532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 31337, + "ts": 667115946226.167, "dur": 4.394, + "args": { + "External id": 234422,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 4533 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::root_post_backward_callback", "pid": 4183440, "tid": 31337, + "ts": 667115946252.240, "dur": 9167.466, + "args": { + "External id": 234423,"Record function id": 0, "Ev Idx": 4534 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate", "pid": 4183440, "tid": 31337, + "ts": 667115946271.914, "dur": 33.010, + "args": { + "External id": 234424,"Record function id": 0, "Ev Idx": 4535 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard", "pid": 4183440, "tid": 31337, + "ts": 667115946310.582, "dur": 257.112, + "args": { + "External id": 234425,"Record function id": 0, "Ev Idx": 4536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce", "pid": 4183440, "tid": 31337, + "ts": 667115946576.634, "dur": 8650.083, + "args": { + "External id": 234426,"Record function id": 0, "Ev Idx": 4537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115946729.888, "dur": 8.918, + "args": { + "External id": 234427,"Record function id": 0, "Concrete Inputs": ["[116925440]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 31337, + "ts": 667115946749.894, "dur": 5.607, + "args": { + "External id": 234428,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[116925440], []], "Ev Idx": 4539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115946775.213, "dur": 7218.327, + "args": { + "External id": 234429,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[], [], [], [14615680, 1]], "Input Dims": [[], [], [], [8, 14615680]], "Ev Idx": 4540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 4183440, "tid": 31337, + "ts": 667115946793.431, "dur": 7188.767, + "args": { + "External id": 234430,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[], [], [], [14615680, 1]], "Input Dims": [[], [], [], [8, 14615680]], "Ev Idx": 4541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115946893.519, "dur": 13.663, + "args": { + "External id": 234431,"Record function id": 0, "Concrete Inputs": ["[28789]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 31337, + "ts": 667115946937.774, "dur": 7006.815, + "args": { + "External id": 234432,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[28789], [], [], [], [], [], [], []], "Ev Idx": 4543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 31337, + "ts": 667115946940.630, "dur": 7003.371, + "args": { + "External id": 234433,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[28789], [], [], [], [], [], []], "Ev Idx": 4544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 31337, + "ts": 667115946944.396, "dur": 5.935, + "args": { + "External id": 234434,"Record function id": 0, "Concrete Inputs": ["[28789]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 31337, + "ts": 667115946952.095, "dur": 6987.465, + "args": { + "External id": 234435,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[28789], [28789], []], "Ev Idx": 4546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 31337, + "ts": 667115954115.198, "dur": 9.850, + "args": { + "External id": 234436,"Record function id": 0, "Concrete Inputs": ["", "[14615680]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[116925440], [], [], [], [], []], "Ev Idx": 4547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 31337, + "ts": 667115954118.200, "dur": 6.442, + "args": { + "External id": 234437,"Record function id": 0, "Concrete Inputs": ["[14615680]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 4183440, "tid": 31337, + "ts": 667115954150.750, "dur": 444.440, + "args": { + "External id": 234438,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[14615680], [116925440], [], [], [], []], "Ev Idx": 4549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115954176.669, "dur": 413.150, + "args": { + "External id": 234439,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 14615680, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[116925440], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4550, "In msg nelems": 116925440 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 4183440, "tid": 31337, + "ts": 667115954187.809, "dur": 396.109, + "args": { + "External id": 234440,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[116925440]], "Ev Idx": 4551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 31337, + "ts": 667115954620.485, "dur": 2.243, + "args": { + "External id": 234441,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4552, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954716.613, "dur": 7.081, + "args": { + "External id": 234442,"Record function id": 0, "Concrete Inputs": ["", "[4000, 1024]", "[1024, 1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954766.851, "dur": 1.553, + "args": { + "External id": 234443,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "4096000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954783.311, "dur": 1.459, + "args": { + "External id": 234444,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "4096128"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954796.299, "dur": 0.979, + "args": { + "External id": 234445,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "4227200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954807.148, "dur": 1.109, + "args": { + "External id": 234446,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "4358272"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954817.867, "dur": 1.088, + "args": { + "External id": 234447,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "4489344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954828.074, "dur": 1.388, + "args": { + "External id": 234448,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "4620416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954838.794, "dur": 0.908, + "args": { + "External id": 234449,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "4620544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954849.613, "dur": 1.428, + "args": { + "External id": 234450,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "4980992"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954860.435, "dur": 1.227, + "args": { + "External id": 234451,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "5341440"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954871.130, "dur": 1.235, + "args": { + "External id": 234452,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "5701888"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954881.755, "dur": 0.978, + "args": { + "External id": 234453,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "5702016"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954892.714, "dur": 1.255, + "args": { + "External id": 234454,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "5833088"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954903.058, "dur": 1.225, + "args": { + "External id": 234455,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "5964160"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954914.107, "dur": 1.258, + "args": { + "External id": 234456,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "6095232"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954924.042, "dur": 1.148, + "args": { + "External id": 234457,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6226304"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954933.393, "dur": 1.243, + "args": { + "External id": 234458,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "6226432"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954943.753, "dur": 1.408, + "args": { + "External id": 234459,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "6586880"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954953.497, "dur": 1.200, + "args": { + "External id": 234460,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "6947328"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954963.526, "dur": 1.321, + "args": { + "External id": 234461,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "7307776"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954974.269, "dur": 1.146, + "args": { + "External id": 234462,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "7307904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954984.426, "dur": 1.275, + "args": { + "External id": 234463,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "7438976"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115954994.343, "dur": 0.919, + "args": { + "External id": 234464,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "7570048"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115955004.019, "dur": 1.495, + "args": { + "External id": 234465,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "7701120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115955014.127, "dur": 1.285, + "args": { + "External id": 234466,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "7832192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115955024.677, "dur": 1.129, + "args": { + "External id": 234467,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "7832320"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115955034.166, "dur": 1.273, + "args": { + "External id": 234468,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "8192768"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115955045.090, "dur": 1.197, + "args": { + "External id": 234469,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "8553216"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115955055.684, "dur": 1.246, + "args": { + "External id": 234470,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "8913664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115955067.044, "dur": 1.140, + "args": { + "External id": 234471,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "8913792"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115955077.342, "dur": 1.405, + "args": { + "External id": 234472,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "9044864"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115955087.950, "dur": 0.953, + "args": { + "External id": 234473,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "9175936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115955099.442, "dur": 1.452, + "args": { + "External id": 234474,"Record function id": 0, "Concrete Inputs": ["", "[128, 1024]", "[1024, 1]", "9307008"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115955111.142, "dur": 1.077, + "args": { + "External id": 234475,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "9438080"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115955122.238, "dur": 1.194, + "args": { + "External id": 234476,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "9438208"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115955133.337, "dur": 1.274, + "args": { + "External id": 234477,"Record function id": 0, "Concrete Inputs": ["", "[352, 1024]", "[1024, 1]", "9798656"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115955144.386, "dur": 1.218, + "args": { + "External id": 234478,"Record function id": 0, "Concrete Inputs": ["", "[128, 2816]", "[2816, 1]", "10159104"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115955154.602, "dur": 1.146, + "args": { + "External id": 234479,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "10519552"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 31337, + "ts": 667115955165.567, "dur": 1.322, + "args": { + "External id": 234480,"Record function id": 0, "Concrete Inputs": ["", "[4000, 1024]", "[1024, 1]", "10519680"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4591 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "ProfilerStep#12287", "pid": 4183440, "tid": 4183440, + "ts": 667115182949.403, "dur": 786030.287, + "args": { + "External id": 225793,"Record function id": 0, "Ev Idx": 4592 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.zero_grad#AdamW.zero_grad", "pid": 4183440, "tid": 4183440, + "ts": 667115182981.114, "dur": 395.567, + "args": { + "External id": 225794,"Record function id": 0, "Ev Idx": 4593 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "enumerate(DataLoader)#_StatefulMultiProcessingDataLoaderIter.__next__", "pid": 4183440, "tid": 4183440, + "ts": 667115183417.612, "dur": 2349.472, + "args": { + "External id": 225795,"Record function id": 0, "Ev Idx": 4594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115184560.894, "dur": 7.919, + "args": { + "External id": 225796,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 4183440, "tid": 4183440, + "ts": 667115184591.277, "dur": 6.993, + "args": { + "External id": 225797,"Sequence number": 2757744, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[16, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 4596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115185170.740, "dur": 2.163, + "args": { + "External id": 225798,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 4183440, "tid": 4183440, + "ts": 667115185181.064, "dur": 2.693, + "args": { + "External id": 225799,"Sequence number": 2757744, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[16, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 4598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115185617.712, "dur": 1.840, + "args": { + "External id": 225800,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 4183440, "tid": 4183440, + "ts": 667115185626.314, "dur": 1.855, + "args": { + "External id": 225801,"Sequence number": 2757744, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[16, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 4600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115186268.484, "dur": 13.605, + "args": { + "External id": 225802,"Sequence number": 2757744, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[16, 8192], [], [], [], []], "Ev Idx": 4601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115186276.099, "dur": 2.153, + "args": { + "External id": 225803,"Record function id": 0, "Concrete Inputs": ["", "[16, 8192]", "[8192, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 8192], [], [], []], "Ev Idx": 4602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115186283.578, "dur": 4.315, + "args": { + "External id": 225804,"Sequence number": 2757744, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[16, 8192], [], [], [], []], "Ev Idx": 4603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115186285.850, "dur": 0.988, + "args": { + "External id": 225805,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 8192], [], [], []], "Ev Idx": 4604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115186312.729, "dur": 590.412, + "args": { + "External id": 225806,"Sequence number": 2757744, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], [], [], []], "Ev Idx": 4605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115186320.572, "dur": 581.494, + "args": { + "External id": 225807,"Sequence number": 2757744, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], [], []], "Ev Idx": 4606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115186329.580, "dur": 9.973, + "args": { + "External id": 225808,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "[4096, 1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115186341.901, "dur": 557.798, + "args": { + "External id": 225809,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 4608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115186352.075, "dur": 0.578, + "args": { + "External id": 225810,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], []], "Ev Idx": 4609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand_as", "pid": 4183440, "tid": 4183440, + "ts": 667115186356.073, "dur": 8.574, + "args": { + "External id": 225811,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["long int", "long int"], "Input Strides": [[8192, 1], [4096, 1]], "Input Dims": [[16, 4096], [16, 4096]], "Ev Idx": 4610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 4183440, "tid": 4183440, + "ts": 667115186361.083, "dur": 3.395, + "args": { + "External id": 225812,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], []], "Input Dims": [[16, 4096], [], []], "Ev Idx": 4611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115186363.511, "dur": 0.711, + "args": { + "External id": 225813,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 4612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183440, "tid": 4183440, + "ts": 667115186366.647, "dur": 218.052, + "args": { + "External id": 225814,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 4613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 4183440, + "ts": 667115186369.054, "dur": 215.261, + "args": { + "External id": 225815,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 4614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115186371.395, "dur": 14.597, + "args": { + "External id": 225816,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], []], "Ev Idx": 4615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115186373.351, "dur": 12.133, + "args": { + "External id": 225817,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115186386.851, "dur": 196.495, + "args": { + "External id": 225818,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 4617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115186587.170, "dur": 308.873, + "args": { + "External id": 225819,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 4618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115186923.937, "dur": 523.973, + "args": { + "External id": 225820,"Sequence number": 2757744, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], [], []], "Input Dims": [[16, 8192], [], [], [], [], [], [], []], "Ev Idx": 4619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115186925.959, "dur": 521.123, + "args": { + "External id": 225821,"Sequence number": 2757744, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], []], "Input Dims": [[16, 8192], [], [], [], [], [], []], "Ev Idx": 4620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115186934.227, "dur": 8.008, + "args": { + "External id": 225822,"Record function id": 0, "Concrete Inputs": ["[16, 8192]", "[8192, 1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115186943.672, "dur": 500.942, + "args": { + "External id": 225823,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[8192, 1], [8192, 1], []], "Input Dims": [[16, 8192], [16, 8192], []], "Ev Idx": 4622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::arange", "pid": 4183440, "tid": 4183440, + "ts": 667115187473.378, "dur": 71.612, + "args": { + "External id": 225824,"Record function id": 0, "Concrete Inputs": ["0", "4096", "", "", "", "False"], "Input type": ["Scalar", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115187477.816, "dur": 4.204, + "args": { + "External id": 225825,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::arange", "pid": 4183440, "tid": 4183440, + "ts": 667115187484.367, "dur": 60.114, + "args": { + "External id": 225826,"Record function id": 0, "Concrete Inputs": ["0", "4096", "1", ""], "Input type": ["Scalar", "Scalar", "Scalar", "long int"], "Input Strides": [[], [], [], [1]], "Input Dims": [[], [], [], [0]], "Ev Idx": 4625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115187489.242, "dur": 24.566, + "args": { + "External id": 225827,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["long int", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 4626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::repeat", "pid": 4183440, "tid": 4183440, + "ts": 667115187559.178, "dur": 74.594, + "args": { + "External id": 225828,"Sequence number": 2757744, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 4183440, "tid": 4183440, + "ts": 667115187563.602, "dur": 7.517, + "args": { + "External id": 225829,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[4096], [], []], "Ev Idx": 4628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115187568.973, "dur": 1.852, + "args": { + "External id": 225830,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096]", "[4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 4629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115187572.237, "dur": 4.482, + "args": { + "External id": 225831,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 4183440, "tid": 4183440, + "ts": 667115187581.513, "dur": 3.601, + "args": { + "External id": 225832,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[4096, 1]], "Input Dims": [[16, 4096]], "Ev Idx": 4631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 4183440, "tid": 4183440, + "ts": 667115187587.701, "dur": 5.244, + "args": { + "External id": 225833,"Record function id": 0, "Concrete Inputs": ["", "0", "1", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 4632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115187592.078, "dur": 0.667, + "args": { + "External id": 225834,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1]", "[4096, 1, 4096]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 4633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 4183440, "tid": 4183440, + "ts": 667115187593.723, "dur": 4.970, + "args": { + "External id": 225835,"Record function id": 0, "Concrete Inputs": ["", "1", "4096", "4096"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 4096], [], [], []], "Input Dims": [[16, 4096, 1], [], [], []], "Ev Idx": 4634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115187597.841, "dur": 0.772, + "args": { + "External id": 225836,"Record function id": 0, "Concrete Inputs": ["", "[16, 1, 1, 4096]", "[4096, 4096, 4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1, 4096], [], [], []], "Input Dims": [[16, 4096, 1], [], [], []], "Ev Idx": 4635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand_as", "pid": 4183440, "tid": 4183440, + "ts": 667115187601.675, "dur": 4.568, + "args": { + "External id": 225837,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["long int", "long int"], "Input Strides": [[4096, 1], [4096, 4096, 4096, 1]], "Input Dims": [[1, 4096], [16, 1, 1, 4096]], "Ev Idx": 4636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 4183440, "tid": 4183440, + "ts": 667115187603.575, "dur": 2.558, + "args": { + "External id": 225838,"Record function id": 0, "Concrete Inputs": ["", "[16, 1, 1, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1, 4096], [], []], "Ev Idx": 4637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115187605.100, "dur": 0.941, + "args": { + "External id": 225839,"Record function id": 0, "Concrete Inputs": ["", "[16, 1, 1, 4096]", "[0, 4096, 4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 4638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115187607.380, "dur": 25.466, + "args": { + "External id": 225840,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 4096, 4096, 1], [0, 4096, 4096, 1], []], "Input Dims": [[16, 1, 1, 4096], [16, 1, 1, 4096], []], "Ev Idx": 4639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115187642.300, "dur": 74.309, + "args": { + "External id": 225841,"Sequence number": 2757744, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], []], "Ev Idx": 4640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115187644.137, "dur": 72.245, + "args": { + "External id": 225842,"Sequence number": 2757744, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], [], []], "Ev Idx": 4641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115187688.344, "dur": 4.980, + "args": { + "External id": 225843,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "[4096, 1]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115187694.853, "dur": 20.938, + "args": { + "External id": 225844,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 4643 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::root_pre_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115187832.573, "dur": 147.982, + "args": { + "External id": 225845,"Record function id": 0, "Ev Idx": 4644 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::inputs_to_device", "pid": 4183440, "tid": 4183440, + "ts": 667115187911.287, "dur": 59.348, + "args": { + "External id": 225846,"Record function id": 0, "Ev Idx": 4645 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115187987.607, "dur": 41.405, + "args": { + "External id": 225847,"Record function id": 0, "Ev Idx": 4646 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115188037.541, "dur": 7654.026, + "args": { + "External id": 225848,"Record function id": 0, "Ev Idx": 4647 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather", "pid": 4183440, "tid": 4183440, + "ts": 667115188046.729, "dur": 1310.233, + "args": { + "External id": 225849,"Record function id": 0, "Ev Idx": 4648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115188143.348, "dur": 6.326, + "args": { + "External id": 225850,"Record function id": 0, "Concrete Inputs": ["[14615680]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115188165.356, "dur": 133.750, + "args": { + "External id": 225851,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["c10::BFloat16", "", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[14615680], [], []], "Ev Idx": 4650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188170.327, "dur": 1.489, + "args": { + "External id": 225852,"Record function id": 0, "Concrete Inputs": ["", "[4096000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188178.147, "dur": 0.340, + "args": { + "External id": 225853,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "4096000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188179.516, "dur": 0.548, + "args": { + "External id": 225854,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "4096128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188180.808, "dur": 1.848, + "args": { + "External id": 225855,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "4227200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188188.478, "dur": 0.401, + "args": { + "External id": 225856,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "4358272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188189.898, "dur": 0.256, + "args": { + "External id": 225857,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "4489344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188191.004, "dur": 2.650, + "args": { + "External id": 225858,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "4620416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188196.740, "dur": 0.398, + "args": { + "External id": 225859,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "4620544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188198.152, "dur": 0.164, + "args": { + "External id": 225860,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "4980992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188203.546, "dur": 0.312, + "args": { + "External id": 225861,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "5341440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188204.712, "dur": 0.215, + "args": { + "External id": 225862,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "5701888"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188205.580, "dur": 1.329, + "args": { + "External id": 225863,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "5702016"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188213.005, "dur": 0.384, + "args": { + "External id": 225864,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "5833088"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188214.002, "dur": 0.167, + "args": { + "External id": 225865,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "5964160"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188214.940, "dur": 2.299, + "args": { + "External id": 225866,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6095232"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188219.941, "dur": 0.430, + "args": { + "External id": 225867,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6226304"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188221.018, "dur": 0.353, + "args": { + "External id": 225868,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6226432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188226.732, "dur": 0.159, + "args": { + "External id": 225869,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6586880"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188227.746, "dur": 0.203, + "args": { + "External id": 225870,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6947328"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188228.785, "dur": 1.471, + "args": { + "External id": 225871,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "7307776"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188235.313, "dur": 0.183, + "args": { + "External id": 225872,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "7307904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188236.155, "dur": 0.164, + "args": { + "External id": 225873,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "7438976"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188237.026, "dur": 2.352, + "args": { + "External id": 225874,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "7570048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188242.591, "dur": 0.173, + "args": { + "External id": 225875,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "7701120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188243.451, "dur": 0.182, + "args": { + "External id": 225876,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "7832192"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188248.518, "dur": 0.174, + "args": { + "External id": 225877,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7832320"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188249.449, "dur": 0.354, + "args": { + "External id": 225878,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "8192768"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188250.579, "dur": 1.228, + "args": { + "External id": 225879,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "8553216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188256.009, "dur": 0.173, + "args": { + "External id": 225880,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "8913664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188256.778, "dur": 0.159, + "args": { + "External id": 225881,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "8913792"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188257.615, "dur": 2.502, + "args": { + "External id": 225882,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "9044864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188263.023, "dur": 0.170, + "args": { + "External id": 225883,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "9175936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188263.889, "dur": 0.188, + "args": { + "External id": 225884,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "9307008"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188268.718, "dur": 0.157, + "args": { + "External id": 225885,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "9438080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188269.544, "dur": 0.161, + "args": { + "External id": 225886,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "9438208"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188270.373, "dur": 1.613, + "args": { + "External id": 225887,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "9798656"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188277.188, "dur": 0.197, + "args": { + "External id": 225888,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "10159104"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188278.116, "dur": 0.151, + "args": { + "External id": 225889,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "10519552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188278.923, "dur": 2.254, + "args": { + "External id": 225890,"Record function id": 0, "Concrete Inputs": ["", "[4096000]", "[1]", "10519680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115188324.075, "dur": 48.782, + "args": { + "External id": 225891,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 4690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115188435.484, "dur": 393.804, + "args": { + "External id": 225892,"Record function id": 0, "Concrete Inputs": ["", "", "14615680", "8", "4", "15", ""], "Input type": ["TensorList", "", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 4691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115188449.652, "dur": 4.143, + "args": { + "External id": 225893,"Record function id": 0, "Concrete Inputs": ["[116925440]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115188460.028, "dur": 13.253, + "args": { + "External id": 225894,"Record function id": 0, "Concrete Inputs": ["", "0", "58462720", "14615680"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[116925440], [], [], []], "Ev Idx": 4693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115188464.608, "dur": 8.251, + "args": { + "External id": 225895,"Record function id": 0, "Concrete Inputs": ["", "0", "58462720", "73078400", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[116925440], [], [], [], []], "Ev Idx": 4694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188469.595, "dur": 0.463, + "args": { + "External id": 225896,"Record function id": 0, "Concrete Inputs": ["", "[14615680]", "[1]", "58462720"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[116925440], [], [], []], "Ev Idx": 4695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115188481.304, "dur": 257.762, + "args": { + "External id": 225897,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["c10::BFloat16", "", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[14615680], [], []], "Ev Idx": 4696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188482.924, "dur": 0.418, + "args": { + "External id": 225898,"Record function id": 0, "Concrete Inputs": ["", "[4096000]", "[1]", "58462720"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188484.540, "dur": 0.399, + "args": { + "External id": 225899,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "62558720"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188488.043, "dur": 96.728, + "args": { + "External id": 225900,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "62558848"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188587.158, "dur": 1.156, + "args": { + "External id": 225901,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "62689920"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188591.692, "dur": 0.415, + "args": { + "External id": 225902,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "62820992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188592.898, "dur": 0.613, + "args": { + "External id": 225903,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "62952064"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188594.960, "dur": 0.422, + "args": { + "External id": 225904,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "63083136"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188598.409, "dur": 0.267, + "args": { + "External id": 225905,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "63083264"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188599.534, "dur": 0.761, + "args": { + "External id": 225906,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "63443712"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188600.942, "dur": 0.392, + "args": { + "External id": 225907,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "63804160"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188604.355, "dur": 1.655, + "args": { + "External id": 225908,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "64164608"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188607.207, "dur": 0.224, + "args": { + "External id": 225909,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "64164736"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188610.120, "dur": 2.954, + "args": { + "External id": 225910,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "64295808"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188613.848, "dur": 0.576, + "args": { + "External id": 225911,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "64426880"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188615.128, "dur": 0.407, + "args": { + "External id": 225912,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "64557952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188621.142, "dur": 0.302, + "args": { + "External id": 225913,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "64689024"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188622.071, "dur": 0.345, + "args": { + "External id": 225914,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "64689152"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188623.242, "dur": 0.395, + "args": { + "External id": 225915,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "65049600"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188628.284, "dur": 1.608, + "args": { + "External id": 225916,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "65410048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188630.342, "dur": 0.395, + "args": { + "External id": 225917,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "65770496"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188633.151, "dur": 2.535, + "args": { + "External id": 225918,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "65770624"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188636.460, "dur": 0.384, + "args": { + "External id": 225919,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "65901696"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188637.522, "dur": 0.199, + "args": { + "External id": 225920,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "66032768"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188642.540, "dur": 0.168, + "args": { + "External id": 225921,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "66163840"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188643.521, "dur": 0.181, + "args": { + "External id": 225922,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "66294912"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188644.331, "dur": 0.167, + "args": { + "External id": 225923,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "66295040"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188650.391, "dur": 38.216, + "args": { + "External id": 225924,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "66655488"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188691.057, "dur": 0.283, + "args": { + "External id": 225925,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "67015936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188693.792, "dur": 2.610, + "args": { + "External id": 225926,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "67376384"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188697.439, "dur": 0.259, + "args": { + "External id": 225927,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "67376512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188698.556, "dur": 0.342, + "args": { + "External id": 225928,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "67507584"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188704.669, "dur": 0.255, + "args": { + "External id": 225929,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "67638656"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188705.872, "dur": 0.161, + "args": { + "External id": 225930,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "67769728"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188706.704, "dur": 0.193, + "args": { + "External id": 225931,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "67900800"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188712.149, "dur": 1.474, + "args": { + "External id": 225932,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "67900928"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188714.668, "dur": 0.547, + "args": { + "External id": 225933,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "68261376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188717.805, "dur": 2.301, + "args": { + "External id": 225934,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "68621824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188720.853, "dur": 0.357, + "args": { + "External id": 225935,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "68982272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115188721.697, "dur": 0.380, + "args": { + "External id": 225936,"Record function id": 0, "Concrete Inputs": ["", "[4096000]", "[1]", "68982400"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[14615680], [], [], []], "Ev Idx": 4735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115188768.339, "dur": 42.595, + "args": { + "External id": 225937,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 4736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115188893.034, "dur": 355.714, + "args": { + "External id": 225938,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[116925440], [14615680], [], [], []], "Ev Idx": 4737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115188927.901, "dur": 316.284, + "args": { + "External id": 225939,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 116925440, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[14615680], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4738, "In msg nelems": 14615680 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115188938.776, "dur": 300.603, + "args": { + "External id": 225940,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[14615680]], "Ev Idx": 4739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115189273.778, "dur": 2.299, + "args": { + "External id": 225941,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4740, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out", "pid": 4183440, "tid": 4183440, + "ts": 667115189372.364, "dur": 6087.076, + "args": { + "External id": 225942,"Record function id": 0, "Ev Idx": 4741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189570.970, "dur": 7.200, + "args": { + "External id": 225943,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[116925440], []], "Ev Idx": 4742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189582.028, "dur": 1.312, + "args": { + "External id": 225944,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[32768000], []], "Ev Idx": 4743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189585.178, "dur": 1.113, + "args": { + "External id": 225945,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189588.004, "dur": 2.245, + "args": { + "External id": 225946,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189594.049, "dur": 1.029, + "args": { + "External id": 225947,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189596.562, "dur": 0.890, + "args": { + "External id": 225948,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189599.336, "dur": 0.878, + "args": { + "External id": 225949,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189601.852, "dur": 2.104, + "args": { + "External id": 225950,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189610.401, "dur": 0.463, + "args": { + "External id": 225951,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189612.175, "dur": 0.637, + "args": { + "External id": 225952,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189614.308, "dur": 0.556, + "args": { + "External id": 225953,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189616.335, "dur": 1.768, + "args": { + "External id": 225954,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189621.648, "dur": 0.704, + "args": { + "External id": 225955,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189623.716, "dur": 0.811, + "args": { + "External id": 225956,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189625.834, "dur": 0.807, + "args": { + "External id": 225957,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189627.814, "dur": 1.313, + "args": { + "External id": 225958,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189634.950, "dur": 0.655, + "args": { + "External id": 225959,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189637.026, "dur": 0.622, + "args": { + "External id": 225960,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189639.202, "dur": 0.757, + "args": { + "External id": 225961,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189641.128, "dur": 1.710, + "args": { + "External id": 225962,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189646.214, "dur": 0.884, + "args": { + "External id": 225963,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189648.676, "dur": 1.019, + "args": { + "External id": 225964,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189651.102, "dur": 35.180, + "args": { + "External id": 225965,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189690.234, "dur": 1.605, + "args": { + "External id": 225966,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189714.682, "dur": 0.696, + "args": { + "External id": 225967,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189716.859, "dur": 0.806, + "args": { + "External id": 225968,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189719.681, "dur": 0.741, + "args": { + "External id": 225969,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189721.680, "dur": 1.867, + "args": { + "External id": 225970,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189727.143, "dur": 0.821, + "args": { + "External id": 225971,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189729.263, "dur": 0.813, + "args": { + "External id": 225972,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189731.512, "dur": 0.724, + "args": { + "External id": 225973,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189733.557, "dur": 2.092, + "args": { + "External id": 225974,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189741.142, "dur": 0.928, + "args": { + "External id": 225975,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189743.716, "dur": 0.400, + "args": { + "External id": 225976,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189745.769, "dur": 0.653, + "args": { + "External id": 225977,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189747.755, "dur": 1.430, + "args": { + "External id": 225978,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189752.394, "dur": 0.523, + "args": { + "External id": 225979,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189754.179, "dur": 0.754, + "args": { + "External id": 225980,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189756.227, "dur": 0.782, + "args": { + "External id": 225981,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115189758.328, "dur": 1.565, + "args": { + "External id": 225982,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[32768000], []], "Ev Idx": 4781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115189792.819, "dur": 5609.921, + "args": { + "External id": 225983,"Record function id": 0, "Concrete Inputs": ["", "", "1", ""], "Input type": ["c10::BFloat16", "", "Scalar", "TensorList"], "Input Strides": [[14615680, 1], [], [], []], "Input Dims": [[8, 14615680], [], [], []], "Ev Idx": 4782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115189817.191, "dur": 5576.441, + "args": { + "External id": 225984,"Record function id": 0, "Concrete Inputs": ["", "", "1", ""], "Input type": ["c10::BFloat16", "", "Scalar", "TensorList"], "Input Strides": [[14615680, 1], [], [], []], "Input Dims": [[8, 14615680], [], [], []], "Ev Idx": 4783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115189846.059, "dur": 5.864, + "args": { + "External id": 225985,"Record function id": 0, "Concrete Inputs": ["[3034]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115189855.729, "dur": 5498.944, + "args": { + "External id": 225986,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3034], [], [], [], [], [], [], []], "Ev Idx": 4785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115189858.375, "dur": 5495.760, + "args": { + "External id": 225987,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3034], [], [], [], [], [], []], "Ev Idx": 4786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115189865.724, "dur": 5.981, + "args": { + "External id": 225988,"Record function id": 0, "Concrete Inputs": ["[3034]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115189873.396, "dur": 5477.648, + "args": { + "External id": 225989,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3034], [3034], []], "Ev Idx": 4788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115195774.821, "dur": 42.127, + "args": { + "External id": 225990,"Record function id": 0, "Ev Idx": 4789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 0/0", "pid": 4183440, "tid": 4183440, + "ts": 667115195818.304, "dur": 208.003, + "args": { + "External id": 225991,"Record function id": 0, "Ev Idx": 4790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115195859.950, "dur": 157.173, + "args": { + "External id": 225992,"Sequence number": 2757744, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "long int"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32000, 1024], [16, 4096]], "Ev Idx": 4791 + } + }, + { + "ph": "s", "id": 212, "pid": 4183440, "tid": 4183440, "ts": 667115195859.950, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_0", "pid": 4183440, "tid": 4183440, + "ts": 667115195933.773, "dur": 47.278, + "args": { + "External id": 225993,"kernel_hash": "cfiwphsoqqtbn3caxdjfe3loxe4cx3vmsu3jkzlsi7w2mzdoajqz", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/fi/cfiwphsoqqtbn3caxdjfe3loxe4cx3vmsu3jkzlsi7w2mzdoajqz.py", "kernel_backend": "triton", "Input type": ["long int", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096], [32000, 1024], [16, 4096, 1024], []], "Ev Idx": 4792 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115196089.480, "dur": 56.244, + "args": { + "External id": 225994,"Record function id": 0, "Ev Idx": 4793 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.0)", "pid": 4183440, "tid": 4183440, + "ts": 667115196156.810, "dur": 7067.136, + "args": { + "External id": 225995,"Record function id": 0, "Ev Idx": 4794 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 4183440, "tid": 4183440, + "ts": 667115196165.981, "dur": 908.017, + "args": { + "External id": 225996,"Record function id": 0, "Ev Idx": 4795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115196238.523, "dur": 11.302, + "args": { + "External id": 225997,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115196263.378, "dur": 45.324, + "args": { + "External id": 225998,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 4797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196274.254, "dur": 2.433, + "args": { + "External id": 225999,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196278.240, "dur": 0.453, + "args": { + "External id": 226000,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196279.356, "dur": 2.953, + "args": { + "External id": 226001,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196285.173, "dur": 0.374, + "args": { + "External id": 226002,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196286.141, "dur": 0.579, + "args": { + "External id": 226003,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196290.020, "dur": 0.165, + "args": { + "External id": 226004,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196293.330, "dur": 0.551, + "args": { + "External id": 226005,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196294.717, "dur": 1.636, + "args": { + "External id": 226006,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196302.126, "dur": 0.517, + "args": { + "External id": 226007,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115196318.412, "dur": 39.524, + "args": { + "External id": 226008,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 4807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115196388.411, "dur": 133.428, + "args": { + "External id": 226009,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 4808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115196398.465, "dur": 3.976, + "args": { + "External id": 226010,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115196407.545, "dur": 11.814, + "args": { + "External id": 226011,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 4810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115196411.801, "dur": 7.140, + "args": { + "External id": 226012,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 4811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196417.139, "dur": 0.568, + "args": { + "External id": 226013,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 4812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115196425.687, "dur": 32.319, + "args": { + "External id": 226014,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 4813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196427.333, "dur": 0.481, + "args": { + "External id": 226015,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196431.613, "dur": 0.400, + "args": { + "External id": 226016,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196435.228, "dur": 0.173, + "args": { + "External id": 226017,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196436.020, "dur": 0.382, + "args": { + "External id": 226018,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196439.248, "dur": 4.305, + "args": { + "External id": 226019,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196444.242, "dur": 0.409, + "args": { + "External id": 226020,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196447.341, "dur": 0.398, + "args": { + "External id": 226021,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196451.052, "dur": 0.559, + "args": { + "External id": 226022,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115196452.263, "dur": 0.456, + "args": { + "External id": 226023,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115196469.693, "dur": 41.954, + "args": { + "External id": 226024,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 4823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115196574.037, "dur": 396.883, + "args": { + "External id": 226025,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 4824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115196605.330, "dur": 359.951, + "args": { + "External id": 226026,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4825, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115196617.245, "dur": 340.138, + "args": { + "External id": 226027,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 4826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115196998.817, "dur": 2.628, + "args": { + "External id": 226028,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4827, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 4183440, "tid": 4183440, + "ts": 667115197097.237, "dur": 5930.930, + "args": { + "External id": 226029,"Record function id": 0, "Ev Idx": 4828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115197195.842, "dur": 6.305, + "args": { + "External id": 226030,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 4829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115197205.439, "dur": 0.998, + "args": { + "External id": 226031,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115197208.112, "dur": 1.056, + "args": { + "External id": 226032,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115197210.970, "dur": 1.923, + "args": { + "External id": 226033,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115197214.073, "dur": 1.052, + "args": { + "External id": 226034,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115197218.655, "dur": 0.925, + "args": { + "External id": 226035,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115197220.938, "dur": 0.876, + "args": { + "External id": 226036,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115197223.326, "dur": 2.336, + "args": { + "External id": 226037,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115197229.856, "dur": 0.946, + "args": { + "External id": 226038,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115197235.265, "dur": 1.124, + "args": { + "External id": 226039,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115197253.608, "dur": 5736.299, + "args": { + "External id": 226040,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 4839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115197271.174, "dur": 5712.133, + "args": { + "External id": 226041,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 4840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115197285.964, "dur": 14.355, + "args": { + "External id": 226042,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115197302.903, "dur": 5647.995, + "args": { + "External id": 226043,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 4842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115197305.559, "dur": 5644.811, + "args": { + "External id": 226044,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 4843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115197311.803, "dur": 7.239, + "args": { + "External id": 226045,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115197320.775, "dur": 5626.892, + "args": { + "External id": 226046,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 4845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115203169.491, "dur": 31.042, + "args": { + "External id": 226047,"Sequence number": 2757745, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 4846 + } + }, + { + "ph": "s", "id": 211, "pid": 4183440, "tid": 4183440, "ts": 667115203169.491, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115203185.666, "dur": 10.363, + "args": { + "External id": 226048,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 4847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115203191.519, "dur": 4.275, + "args": { + "External id": 226049,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 4848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115203264.911, "dur": 95.747, + "args": { + "External id": 226050,"Record function id": 0, "Ev Idx": 4849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115203362.044, "dur": 1181.869, + "args": { + "External id": 226051,"Record function id": 0, "Ev Idx": 4850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115203403.739, "dur": 1124.397, + "args": { + "External id": 226052,"Sequence number": 2757746, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 4851 + } + }, + { + "ph": "s", "id": 210, "pid": 4183440, "tid": 4183440, "ts": 667115203403.739, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115203469.454, "dur": 61.390, + "args": { + "External id": 226053,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 4852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115203546.184, "dur": 90.888, + "args": { + "External id": 226054,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115203647.654, "dur": 123.145, + "args": { + "External id": 226055,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115203783.920, "dur": 30.371, + "args": { + "External id": 226056,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115203844.842, "dur": 27.676, + "args": { + "External id": 226057,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115203892.545, "dur": 13.728, + "args": { + "External id": 226058,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115203926.052, "dur": 124.534, + "args": { + "External id": 226059,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 4858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115203974.338, "dur": 10.901, + "args": { + "External id": 226060,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 4859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115203979.159, "dur": 5.384, + "args": { + "External id": 226061,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115203987.669, "dur": 3.537, + "args": { + "External id": 226062,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115203994.571, "dur": 1.114, + "args": { + "External id": 226063,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115203998.041, "dur": 3.323, + "args": { + "External id": 226064,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115204061.725, "dur": 45.907, + "args": { + "External id": 226065,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115204140.879, "dur": 28.072, + "args": { + "External id": 226066,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 4865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115204176.522, "dur": 51.983, + "args": { + "External id": 226067,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 4866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115204238.995, "dur": 42.591, + "args": { + "External id": 226068,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 4867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115204303.404, "dur": 25.410, + "args": { + "External id": 226069,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 4868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115204334.606, "dur": 39.268, + "args": { + "External id": 226070,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 4869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115204399.671, "dur": 19.232, + "args": { + "External id": 226071,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 4870 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.0)", "pid": 4183440, "tid": 4183440, + "ts": 667115204611.892, "dur": 164.304, + "args": { + "External id": 226072,"Record function id": 0, "Ev Idx": 4871 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115204854.057, "dur": 46.585, + "args": { + "External id": 226073,"Record function id": 0, "Ev Idx": 4872 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.1)", "pid": 4183440, "tid": 4183440, + "ts": 667115204909.306, "dur": 9573.059, + "args": { + "External id": 226074,"Record function id": 0, "Ev Idx": 4873 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 4183440, "tid": 4183440, + "ts": 667115204919.107, "dur": 974.443, + "args": { + "External id": 226075,"Record function id": 0, "Ev Idx": 4874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115204998.510, "dur": 9.354, + "args": { + "External id": 226076,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115205021.435, "dur": 45.871, + "args": { + "External id": 226077,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 4876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205029.025, "dur": 4.556, + "args": { + "External id": 226078,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205035.053, "dur": 0.663, + "args": { + "External id": 226079,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205036.775, "dur": 0.551, + "args": { + "External id": 226080,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205043.132, "dur": 0.248, + "args": { + "External id": 226081,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205043.921, "dur": 2.042, + "args": { + "External id": 226082,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205049.003, "dur": 0.397, + "args": { + "External id": 226083,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205052.739, "dur": 0.404, + "args": { + "External id": 226084,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205053.774, "dur": 0.357, + "args": { + "External id": 226085,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205057.312, "dur": 2.680, + "args": { + "External id": 226086,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115205077.040, "dur": 46.500, + "args": { + "External id": 226087,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 4886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115205158.045, "dur": 116.113, + "args": { + "External id": 226088,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 4887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115205168.236, "dur": 3.918, + "args": { + "External id": 226089,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115205177.135, "dur": 11.679, + "args": { + "External id": 226090,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 4889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115205181.589, "dur": 6.766, + "args": { + "External id": 226091,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 4890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205186.573, "dur": 0.555, + "args": { + "External id": 226092,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 4891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115205194.651, "dur": 31.521, + "args": { + "External id": 226093,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 4892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205196.177, "dur": 0.523, + "args": { + "External id": 226094,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205200.201, "dur": 1.875, + "args": { + "External id": 226095,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205202.808, "dur": 3.077, + "args": { + "External id": 226096,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205208.875, "dur": 0.380, + "args": { + "External id": 226097,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205209.844, "dur": 0.190, + "args": { + "External id": 226098,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205213.246, "dur": 0.207, + "args": { + "External id": 226099,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205216.598, "dur": 0.402, + "args": { + "External id": 226100,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205217.782, "dur": 0.366, + "args": { + "External id": 226101,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115205221.662, "dur": 0.558, + "args": { + "External id": 226102,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115205239.901, "dur": 24.961, + "args": { + "External id": 226103,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 4902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115205327.429, "dur": 463.118, + "args": { + "External id": 226104,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 4903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115205360.003, "dur": 424.999, + "args": { + "External id": 226105,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4904, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115205371.908, "dur": 406.880, + "args": { + "External id": 226106,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 4905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115205816.318, "dur": 3.056, + "args": { + "External id": 226107,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4906, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 4183440, "tid": 4183440, + "ts": 667115205913.471, "dur": 8377.216, + "args": { + "External id": 226108,"Record function id": 0, "Ev Idx": 4907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115206003.295, "dur": 6.808, + "args": { + "External id": 226109,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 4908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115206013.463, "dur": 1.150, + "args": { + "External id": 226110,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115206016.499, "dur": 0.678, + "args": { + "External id": 226111,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115206019.017, "dur": 0.886, + "args": { + "External id": 226112,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115206021.478, "dur": 0.787, + "args": { + "External id": 226113,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115206026.319, "dur": 1.040, + "args": { + "External id": 226114,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115206028.958, "dur": 0.792, + "args": { + "External id": 226115,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115206034.255, "dur": 4.038, + "args": { + "External id": 226116,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115206039.480, "dur": 0.782, + "args": { + "External id": 226117,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115206044.178, "dur": 0.892, + "args": { + "External id": 226118,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115206063.490, "dur": 8188.365, + "args": { + "External id": 226119,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 4918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115206083.331, "dur": 8161.546, + "args": { + "External id": 226120,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 4919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115206099.868, "dur": 13.903, + "args": { + "External id": 226121,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115206116.445, "dur": 8095.721, + "args": { + "External id": 226122,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 4921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115206119.025, "dur": 8092.519, + "args": { + "External id": 226123,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 4922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115206124.955, "dur": 5.279, + "args": { + "External id": 226124,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115206132.065, "dur": 8075.922, + "args": { + "External id": 226125,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 4924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115214423.935, "dur": 30.863, + "args": { + "External id": 226126,"Sequence number": 2757747, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 4925 + } + }, + { + "ph": "s", "id": 209, "pid": 4183440, "tid": 4183440, "ts": 667115214423.935, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115214439.494, "dur": 10.592, + "args": { + "External id": 226127,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 4926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115214445.196, "dur": 4.669, + "args": { + "External id": 226128,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 4927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115214565.330, "dur": 134.143, + "args": { + "External id": 226129,"Record function id": 0, "Ev Idx": 4928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115214702.928, "dur": 1088.103, + "args": { + "External id": 226130,"Record function id": 0, "Ev Idx": 4929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115214745.620, "dur": 1031.865, + "args": { + "External id": 226131,"Sequence number": 2757748, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 4930 + } + }, + { + "ph": "s", "id": 208, "pid": 4183440, "tid": 4183440, "ts": 667115214745.620, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115214831.396, "dur": 44.839, + "args": { + "External id": 226132,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 4931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115214893.086, "dur": 91.295, + "args": { + "External id": 226133,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115214992.675, "dur": 34.558, + "args": { + "External id": 226134,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115215032.853, "dur": 28.803, + "args": { + "External id": 226135,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115215092.810, "dur": 24.295, + "args": { + "External id": 226136,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115215132.122, "dur": 16.639, + "args": { + "External id": 226137,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115215164.242, "dur": 126.693, + "args": { + "External id": 226138,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 4937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115215212.186, "dur": 13.614, + "args": { + "External id": 226139,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 4938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115215216.959, "dur": 7.985, + "args": { + "External id": 226140,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115215230.217, "dur": 3.474, + "args": { + "External id": 226141,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115215234.788, "dur": 3.285, + "args": { + "External id": 226142,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115215240.270, "dur": 2.607, + "args": { + "External id": 226143,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115215301.893, "dur": 41.379, + "args": { + "External id": 226144,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 4943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115215373.203, "dur": 27.447, + "args": { + "External id": 226145,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 4944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115215408.819, "dur": 36.979, + "args": { + "External id": 226146,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 4945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115215452.197, "dur": 30.969, + "args": { + "External id": 226147,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 4946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115215536.695, "dur": 25.661, + "args": { + "External id": 226148,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 4947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115215569.018, "dur": 50.797, + "args": { + "External id": 226149,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 4948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115215637.773, "dur": 67.960, + "args": { + "External id": 226150,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 4949 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.1)", "pid": 4183440, "tid": 4183440, + "ts": 667115215857.511, "dur": 77.011, + "args": { + "External id": 226151,"Record function id": 0, "Ev Idx": 4950 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115216004.581, "dur": 44.945, + "args": { + "External id": 226152,"Record function id": 0, "Ev Idx": 4951 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.2)", "pid": 4183440, "tid": 4183440, + "ts": 667115216058.857, "dur": 9019.478, + "args": { + "External id": 226153,"Record function id": 0, "Ev Idx": 4952 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 4183440, "tid": 4183440, + "ts": 667115216069.954, "dur": 942.721, + "args": { + "External id": 226154,"Record function id": 0, "Ev Idx": 4953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115216145.600, "dur": 8.686, + "args": { + "External id": 226155,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115216167.508, "dur": 42.251, + "args": { + "External id": 226156,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 4955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216175.134, "dur": 2.131, + "args": { + "External id": 226157,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216181.146, "dur": 0.507, + "args": { + "External id": 226158,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216184.540, "dur": 0.280, + "args": { + "External id": 226159,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216185.627, "dur": 0.246, + "args": { + "External id": 226160,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216189.043, "dur": 0.342, + "args": { + "External id": 226161,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216192.034, "dur": 0.515, + "args": { + "External id": 226162,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216193.338, "dur": 3.708, + "args": { + "External id": 226163,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216197.790, "dur": 0.487, + "args": { + "External id": 226164,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216201.288, "dur": 0.374, + "args": { + "External id": 226165,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115216220.817, "dur": 41.618, + "args": { + "External id": 226166,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 4965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115216293.700, "dur": 117.706, + "args": { + "External id": 226167,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 4966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115216309.358, "dur": 3.959, + "args": { + "External id": 226168,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115216318.519, "dur": 9.781, + "args": { + "External id": 226169,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 4968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115216322.908, "dur": 4.925, + "args": { + "External id": 226170,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 4969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216325.926, "dur": 0.679, + "args": { + "External id": 226171,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 4970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115216334.551, "dur": 35.274, + "args": { + "External id": 226172,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 4971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216338.235, "dur": 2.524, + "args": { + "External id": 226173,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216341.630, "dur": 0.337, + "args": { + "External id": 226174,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216342.946, "dur": 0.647, + "args": { + "External id": 226175,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216349.039, "dur": 1.618, + "args": { + "External id": 226176,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216351.486, "dur": 0.142, + "args": { + "External id": 226177,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216352.446, "dur": 0.166, + "args": { + "External id": 226178,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216358.030, "dur": 0.141, + "args": { + "External id": 226179,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216358.839, "dur": 0.299, + "args": { + "External id": 226180,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115216361.981, "dur": 2.629, + "args": { + "External id": 226181,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 4980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115216379.684, "dur": 23.581, + "args": { + "External id": 226182,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 4981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115216462.910, "dur": 444.583, + "args": { + "External id": 226183,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 4982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115216522.185, "dur": 379.404, + "args": { + "External id": 226184,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4983, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115216533.555, "dur": 362.123, + "args": { + "External id": 226185,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 4984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115216933.092, "dur": 2.675, + "args": { + "External id": 226186,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4985, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 4183440, "tid": 4183440, + "ts": 667115217035.151, "dur": 7858.368, + "args": { + "External id": 226187,"Record function id": 0, "Ev Idx": 4986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115217132.612, "dur": 6.478, + "args": { + "External id": 226188,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 4987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115217142.374, "dur": 0.945, + "args": { + "External id": 226189,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115217145.086, "dur": 2.183, + "args": { + "External id": 226190,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115217148.986, "dur": 0.938, + "args": { + "External id": 226191,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115217151.610, "dur": 1.066, + "args": { + "External id": 226192,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115217156.295, "dur": 0.760, + "args": { + "External id": 226193,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 4992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115217160.636, "dur": 0.985, + "args": { + "External id": 226194,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 4993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115217162.819, "dur": 1.939, + "args": { + "External id": 226195,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115217165.908, "dur": 0.846, + "args": { + "External id": 226196,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115217170.550, "dur": 0.613, + "args": { + "External id": 226197,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 4996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115217189.278, "dur": 7663.686, + "args": { + "External id": 226198,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 4997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115217207.330, "dur": 7638.581, + "args": { + "External id": 226199,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 4998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115217224.053, "dur": 15.910, + "args": { + "External id": 226200,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115217242.291, "dur": 7569.486, + "args": { + "External id": 226201,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 5000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115217244.522, "dur": 7566.667, + "args": { + "External id": 226202,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 5001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115217250.151, "dur": 4.899, + "args": { + "External id": 226203,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115217256.745, "dur": 7551.151, + "args": { + "External id": 226204,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 5003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115225022.918, "dur": 31.059, + "args": { + "External id": 226205,"Sequence number": 2757749, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 5004 + } + }, + { + "ph": "s", "id": 207, "pid": 4183440, "tid": 4183440, "ts": 667115225022.918, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115225038.864, "dur": 10.339, + "args": { + "External id": 226206,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 5005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115225044.578, "dur": 4.408, + "args": { + "External id": 226207,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 5006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115225117.741, "dur": 87.592, + "args": { + "External id": 226208,"Record function id": 0, "Ev Idx": 5007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115225206.682, "dur": 1105.296, + "args": { + "External id": 226209,"Record function id": 0, "Ev Idx": 5008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115225247.439, "dur": 1050.586, + "args": { + "External id": 226210,"Sequence number": 2757750, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 5009 + } + }, + { + "ph": "s", "id": 206, "pid": 4183440, "tid": 4183440, "ts": 667115225247.439, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115225313.956, "dur": 38.878, + "args": { + "External id": 226211,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115225365.341, "dur": 93.328, + "args": { + "External id": 226212,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115225468.850, "dur": 56.767, + "args": { + "External id": 226213,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115225536.351, "dur": 31.947, + "args": { + "External id": 226214,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115225594.918, "dur": 25.919, + "args": { + "External id": 226215,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115225642.010, "dur": 50.524, + "args": { + "External id": 226216,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115225715.445, "dur": 131.925, + "args": { + "External id": 226217,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 5016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115225767.967, "dur": 12.824, + "args": { + "External id": 226218,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 5017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115225772.553, "dur": 7.437, + "args": { + "External id": 226219,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115225785.344, "dur": 3.826, + "args": { + "External id": 226220,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115225790.296, "dur": 1.096, + "args": { + "External id": 226221,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115225793.568, "dur": 3.872, + "args": { + "External id": 226222,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115225858.986, "dur": 50.620, + "args": { + "External id": 226223,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115225940.089, "dur": 26.607, + "args": { + "External id": 226224,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115225974.645, "dur": 37.176, + "args": { + "External id": 226225,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115226020.225, "dur": 48.397, + "args": { + "External id": 226226,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115226093.658, "dur": 26.094, + "args": { + "External id": 226227,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 5026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115226125.246, "dur": 50.216, + "args": { + "External id": 226228,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 5027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115226198.600, "dur": 21.593, + "args": { + "External id": 226229,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 5028 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.2)", "pid": 4183440, "tid": 4183440, + "ts": 667115226374.540, "dur": 75.036, + "args": { + "External id": 226230,"Record function id": 0, "Ev Idx": 5029 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115226545.182, "dur": 48.563, + "args": { + "External id": 226231,"Record function id": 0, "Ev Idx": 5030 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.3)", "pid": 4183440, "tid": 4183440, + "ts": 667115226603.126, "dur": 8702.153, + "args": { + "External id": 226232,"Record function id": 0, "Ev Idx": 5031 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 4183440, "tid": 4183440, + "ts": 667115226614.744, "dur": 940.293, + "args": { + "External id": 226233,"Record function id": 0, "Ev Idx": 5032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115226731.292, "dur": 9.410, + "args": { + "External id": 226234,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115226754.774, "dur": 46.080, + "args": { + "External id": 226235,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226762.512, "dur": 2.399, + "args": { + "External id": 226236,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226768.910, "dur": 0.361, + "args": { + "External id": 226237,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226772.182, "dur": 0.449, + "args": { + "External id": 226238,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226778.483, "dur": 0.289, + "args": { + "External id": 226239,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226781.932, "dur": 0.523, + "args": { + "External id": 226240,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226785.726, "dur": 0.258, + "args": { + "External id": 226241,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226786.571, "dur": 3.214, + "args": { + "External id": 226242,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226790.646, "dur": 0.197, + "args": { + "External id": 226243,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226793.933, "dur": 0.257, + "args": { + "External id": 226244,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115226811.199, "dur": 43.991, + "args": { + "External id": 226245,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115226888.531, "dur": 129.920, + "args": { + "External id": 226246,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 5045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115226903.843, "dur": 4.019, + "args": { + "External id": 226247,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115226912.455, "dur": 9.757, + "args": { + "External id": 226248,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115226917.100, "dur": 4.678, + "args": { + "External id": 226249,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 5048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226919.807, "dur": 0.739, + "args": { + "External id": 226250,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115226928.667, "dur": 32.346, + "args": { + "External id": 226251,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226932.266, "dur": 2.408, + "args": { + "External id": 226252,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226935.423, "dur": 0.345, + "args": { + "External id": 226253,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226936.524, "dur": 0.326, + "args": { + "External id": 226254,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226942.921, "dur": 1.819, + "args": { + "External id": 226255,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226945.333, "dur": 0.531, + "args": { + "External id": 226256,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226946.501, "dur": 0.202, + "args": { + "External id": 226257,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226950.073, "dur": 0.241, + "args": { + "External id": 226258,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226950.927, "dur": 0.319, + "args": { + "External id": 226259,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115226953.674, "dur": 2.673, + "args": { + "External id": 226260,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115226985.229, "dur": 24.979, + "args": { + "External id": 226261,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115227070.422, "dur": 371.132, + "args": { + "External id": 226262,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 5061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115227103.917, "dur": 332.811, + "args": { + "External id": 226263,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5062, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115227115.532, "dur": 316.161, + "args": { + "External id": 226264,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 5063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115227461.752, "dur": 2.356, + "args": { + "External id": 226265,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5064, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 4183440, "tid": 4183440, + "ts": 667115227578.073, "dur": 7533.396, + "args": { + "External id": 226266,"Record function id": 0, "Ev Idx": 5065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115227709.424, "dur": 6.810, + "args": { + "External id": 226267,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 5066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115227719.618, "dur": 1.359, + "args": { + "External id": 226268,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115227722.759, "dur": 2.746, + "args": { + "External id": 226269,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115227727.174, "dur": 0.866, + "args": { + "External id": 226270,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115227729.729, "dur": 0.924, + "args": { + "External id": 226271,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115227734.406, "dur": 1.111, + "args": { + "External id": 226272,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115227738.986, "dur": 0.769, + "args": { + "External id": 226273,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115227741.235, "dur": 2.910, + "args": { + "External id": 226274,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115227745.338, "dur": 0.820, + "args": { + "External id": 226275,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115227749.930, "dur": 0.729, + "args": { + "External id": 226276,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115227768.973, "dur": 7303.100, + "args": { + "External id": 226277,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115227787.424, "dur": 7277.567, + "args": { + "External id": 226278,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115227804.004, "dur": 15.448, + "args": { + "External id": 226279,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115227822.088, "dur": 7208.406, + "args": { + "External id": 226280,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 5079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115227824.631, "dur": 7205.369, + "args": { + "External id": 226281,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 5080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115227830.072, "dur": 5.799, + "args": { + "External id": 226282,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115227837.543, "dur": 7189.263, + "args": { + "External id": 226283,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 5082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115235239.717, "dur": 41.760, + "args": { + "External id": 226284,"Sequence number": 2757751, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 5083 + } + }, + { + "ph": "s", "id": 205, "pid": 4183440, "tid": 4183440, "ts": 667115235239.717, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115235266.695, "dur": 10.201, + "args": { + "External id": 226285,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 5084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115235272.502, "dur": 4.190, + "args": { + "External id": 226286,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 5085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115235345.572, "dur": 84.545, + "args": { + "External id": 226287,"Record function id": 0, "Ev Idx": 5086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115235431.619, "dur": 1160.070, + "args": { + "External id": 226288,"Record function id": 0, "Ev Idx": 5087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115235469.995, "dur": 1106.920, + "args": { + "External id": 226289,"Sequence number": 2757752, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 5088 + } + }, + { + "ph": "s", "id": 204, "pid": 4183440, "tid": 4183440, "ts": 667115235469.995, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115235555.988, "dur": 43.224, + "args": { + "External id": 226290,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115235612.276, "dur": 129.118, + "args": { + "External id": 226291,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115235757.714, "dur": 37.939, + "args": { + "External id": 226292,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115235801.389, "dur": 29.630, + "args": { + "External id": 226293,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115235863.432, "dur": 31.283, + "args": { + "External id": 226294,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115235915.881, "dur": 20.930, + "args": { + "External id": 226295,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115235961.675, "dur": 133.485, + "args": { + "External id": 226296,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 5095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115236013.061, "dur": 10.883, + "args": { + "External id": 226297,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 5096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115236017.938, "dur": 5.158, + "args": { + "External id": 226298,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115236028.909, "dur": 4.725, + "args": { + "External id": 226299,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115236034.908, "dur": 0.867, + "args": { + "External id": 226300,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115236040.122, "dur": 3.187, + "args": { + "External id": 226301,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115236105.732, "dur": 46.701, + "args": { + "External id": 226302,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115236181.613, "dur": 26.700, + "args": { + "External id": 226303,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115236217.334, "dur": 36.966, + "args": { + "External id": 226304,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115236288.767, "dur": 46.323, + "args": { + "External id": 226305,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115236364.064, "dur": 24.006, + "args": { + "External id": 226306,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 5105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115236394.314, "dur": 54.150, + "args": { + "External id": 226307,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 5106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115236466.273, "dur": 21.796, + "args": { + "External id": 226308,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 5107 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.3)", "pid": 4183440, "tid": 4183440, + "ts": 667115236692.997, "dur": 82.008, + "args": { + "External id": 226309,"Record function id": 0, "Ev Idx": 5108 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115236850.805, "dur": 47.437, + "args": { + "External id": 226310,"Record function id": 0, "Ev Idx": 5109 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.4)", "pid": 4183440, "tid": 4183440, + "ts": 667115236907.089, "dur": 8871.526, + "args": { + "External id": 226311,"Record function id": 0, "Ev Idx": 5110 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 4183440, "tid": 4183440, + "ts": 667115236917.882, "dur": 941.355, + "args": { + "External id": 226312,"Record function id": 0, "Ev Idx": 5111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115236998.864, "dur": 9.512, + "args": { + "External id": 226313,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115237022.068, "dur": 42.161, + "args": { + "External id": 226314,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237029.692, "dur": 2.240, + "args": { + "External id": 226315,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237035.699, "dur": 0.214, + "args": { + "External id": 226316,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237039.290, "dur": 0.226, + "args": { + "External id": 226317,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237040.369, "dur": 0.487, + "args": { + "External id": 226318,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237043.983, "dur": 0.665, + "args": { + "External id": 226319,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237048.079, "dur": 0.350, + "args": { + "External id": 226320,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237049.154, "dur": 3.750, + "args": { + "External id": 226321,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237053.723, "dur": 0.391, + "args": { + "External id": 226322,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237056.862, "dur": 0.292, + "args": { + "External id": 226323,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115237075.165, "dur": 44.567, + "args": { + "External id": 226324,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115237151.723, "dur": 113.170, + "args": { + "External id": 226325,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 5124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115237166.787, "dur": 3.642, + "args": { + "External id": 226326,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115237175.407, "dur": 9.426, + "args": { + "External id": 226327,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115237179.989, "dur": 4.398, + "args": { + "External id": 226328,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 5127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237182.729, "dur": 0.543, + "args": { + "External id": 226329,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115237190.502, "dur": 33.845, + "args": { + "External id": 226330,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237194.267, "dur": 2.241, + "args": { + "External id": 226331,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237197.422, "dur": 0.384, + "args": { + "External id": 226332,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237198.653, "dur": 0.417, + "args": { + "External id": 226333,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237204.242, "dur": 1.577, + "args": { + "External id": 226334,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237206.615, "dur": 0.251, + "args": { + "External id": 226335,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237207.641, "dur": 0.419, + "args": { + "External id": 226336,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237212.547, "dur": 0.165, + "args": { + "External id": 226337,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237213.690, "dur": 0.454, + "args": { + "External id": 226338,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115237217.107, "dur": 2.275, + "args": { + "External id": 226339,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115237234.174, "dur": 22.955, + "args": { + "External id": 226340,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115237317.035, "dur": 440.052, + "args": { + "External id": 226341,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 5140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115237352.580, "dur": 398.363, + "args": { + "External id": 226342,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5141, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115237363.105, "dur": 381.500, + "args": { + "External id": 226343,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 5142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115237782.283, "dur": 2.502, + "args": { + "External id": 226344,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5143, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 4183440, "tid": 4183440, + "ts": 667115237879.516, "dur": 7672.626, + "args": { + "External id": 226345,"Record function id": 0, "Ev Idx": 5144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115237970.928, "dur": 6.527, + "args": { + "External id": 226346,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 5145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115237980.791, "dur": 1.074, + "args": { + "External id": 226347,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115237983.539, "dur": 2.323, + "args": { + "External id": 226348,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115237987.548, "dur": 1.038, + "args": { + "External id": 226349,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115237990.064, "dur": 1.001, + "args": { + "External id": 226350,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115237992.574, "dur": 0.848, + "args": { + "External id": 226351,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115237998.516, "dur": 0.829, + "args": { + "External id": 226352,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115238000.891, "dur": 3.158, + "args": { + "External id": 226353,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115238005.401, "dur": 0.697, + "args": { + "External id": 226354,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115238007.396, "dur": 0.525, + "args": { + "External id": 226355,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115238028.237, "dur": 7459.799, + "args": { + "External id": 226356,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115238046.333, "dur": 7434.951, + "args": { + "External id": 226357,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115238063.325, "dur": 15.016, + "args": { + "External id": 226358,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115238081.277, "dur": 7368.738, + "args": { + "External id": 226359,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 5158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115238083.941, "dur": 7365.472, + "args": { + "External id": 226360,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 5159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115238089.831, "dur": 4.799, + "args": { + "External id": 226361,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115238096.500, "dur": 7349.347, + "args": { + "External id": 226362,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 5161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115245721.734, "dur": 31.099, + "args": { + "External id": 226363,"Sequence number": 2757753, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 5162 + } + }, + { + "ph": "s", "id": 203, "pid": 4183440, "tid": 4183440, "ts": 667115245721.734, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115245738.440, "dur": 9.760, + "args": { + "External id": 226364,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 5163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115245743.385, "dur": 4.489, + "args": { + "External id": 226365,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 5164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115245818.063, "dur": 88.354, + "args": { + "External id": 226366,"Record function id": 0, "Ev Idx": 5165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115245907.919, "dur": 1097.616, + "args": { + "External id": 226367,"Record function id": 0, "Ev Idx": 5166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115245948.797, "dur": 1042.642, + "args": { + "External id": 226368,"Sequence number": 2757754, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 5167 + } + }, + { + "ph": "s", "id": 202, "pid": 4183440, "tid": 4183440, "ts": 667115245948.797, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115246013.148, "dur": 44.731, + "args": { + "External id": 226369,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115246070.367, "dur": 94.200, + "args": { + "External id": 226370,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115246173.131, "dur": 35.017, + "args": { + "External id": 226371,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115246216.282, "dur": 28.570, + "args": { + "External id": 226372,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115246269.530, "dur": 25.838, + "args": { + "External id": 226373,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115246312.001, "dur": 14.398, + "args": { + "External id": 226374,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115246344.239, "dur": 126.126, + "args": { + "External id": 226375,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 5174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115246392.196, "dur": 9.478, + "args": { + "External id": 226376,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 5175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115246396.098, "dur": 4.938, + "args": { + "External id": 226377,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115246405.843, "dur": 6.391, + "args": { + "External id": 226378,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115246413.436, "dur": 0.893, + "args": { + "External id": 226379,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115246416.545, "dur": 3.475, + "args": { + "External id": 226380,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115246480.682, "dur": 68.364, + "args": { + "External id": 226381,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115246581.965, "dur": 28.656, + "args": { + "External id": 226382,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115246618.613, "dur": 80.508, + "args": { + "External id": 226383,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115246711.295, "dur": 53.812, + "args": { + "External id": 226384,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115246791.944, "dur": 25.956, + "args": { + "External id": 226385,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 5184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115246824.006, "dur": 49.867, + "args": { + "External id": 226386,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 5185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115246893.414, "dur": 19.779, + "args": { + "External id": 226387,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 5186 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.4)", "pid": 4183440, "tid": 4183440, + "ts": 667115247071.939, "dur": 76.469, + "args": { + "External id": 226388,"Record function id": 0, "Ev Idx": 5187 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115247223.611, "dur": 47.691, + "args": { + "External id": 226389,"Record function id": 0, "Ev Idx": 5188 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.5)", "pid": 4183440, "tid": 4183440, + "ts": 667115247280.260, "dur": 8808.705, + "args": { + "External id": 226390,"Record function id": 0, "Ev Idx": 5189 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 4183440, "tid": 4183440, + "ts": 667115247292.032, "dur": 958.882, + "args": { + "External id": 226391,"Record function id": 0, "Ev Idx": 5190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115247370.137, "dur": 8.067, + "args": { + "External id": 226392,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115247391.856, "dur": 41.026, + "args": { + "External id": 226393,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247398.621, "dur": 2.316, + "args": { + "External id": 226394,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247405.217, "dur": 0.273, + "args": { + "External id": 226395,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247408.565, "dur": 0.216, + "args": { + "External id": 226396,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247409.575, "dur": 0.439, + "args": { + "External id": 226397,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247413.427, "dur": 0.335, + "args": { + "External id": 226398,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247416.117, "dur": 0.416, + "args": { + "External id": 226399,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247417.129, "dur": 4.403, + "args": { + "External id": 226400,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247422.464, "dur": 0.232, + "args": { + "External id": 226401,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247424.732, "dur": 0.357, + "args": { + "External id": 226402,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115247443.194, "dur": 41.939, + "args": { + "External id": 226403,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115247541.734, "dur": 182.163, + "args": { + "External id": 226404,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 5203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115247556.318, "dur": 5.571, + "args": { + "External id": 226405,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115247567.253, "dur": 10.527, + "args": { + "External id": 226406,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115247571.904, "dur": 5.447, + "args": { + "External id": 226407,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 5206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247575.236, "dur": 0.646, + "args": { + "External id": 226408,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115247583.999, "dur": 31.081, + "args": { + "External id": 226409,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247587.617, "dur": 2.616, + "args": { + "External id": 226410,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247591.555, "dur": 0.366, + "args": { + "External id": 226411,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247592.547, "dur": 0.297, + "args": { + "External id": 226412,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247597.694, "dur": 1.711, + "args": { + "External id": 226413,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247600.013, "dur": 0.298, + "args": { + "External id": 226414,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247600.951, "dur": 0.318, + "args": { + "External id": 226415,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247604.284, "dur": 0.405, + "args": { + "External id": 226416,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247605.408, "dur": 0.171, + "args": { + "External id": 226417,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115247607.554, "dur": 2.319, + "args": { + "External id": 226418,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115247630.918, "dur": 81.690, + "args": { + "External id": 226419,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115247786.230, "dur": 373.433, + "args": { + "External id": 226420,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 5219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115247821.167, "dur": 333.499, + "args": { + "External id": 226421,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5220, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115247831.734, "dur": 317.548, + "args": { + "External id": 226422,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 5221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115248181.442, "dur": 2.287, + "args": { + "External id": 226423,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5222, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 4183440, "tid": 4183440, + "ts": 667115248271.749, "dur": 7629.463, + "args": { + "External id": 226424,"Record function id": 0, "Ev Idx": 5223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115248358.813, "dur": 6.196, + "args": { + "External id": 226425,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 5224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115248368.146, "dur": 1.177, + "args": { + "External id": 226426,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115248371.242, "dur": 2.353, + "args": { + "External id": 226427,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115248375.230, "dur": 1.052, + "args": { + "External id": 226428,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115248377.573, "dur": 0.898, + "args": { + "External id": 226429,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115248379.946, "dur": 0.711, + "args": { + "External id": 226430,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115248385.955, "dur": 0.829, + "args": { + "External id": 226431,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115248388.590, "dur": 2.158, + "args": { + "External id": 226432,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115248391.978, "dur": 0.950, + "args": { + "External id": 226433,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115248394.318, "dur": 0.884, + "args": { + "External id": 226434,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115248415.403, "dur": 7444.171, + "args": { + "External id": 226435,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115248439.008, "dur": 7413.681, + "args": { + "External id": 226436,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115248453.865, "dur": 15.382, + "args": { + "External id": 226437,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115248471.961, "dur": 7347.820, + "args": { + "External id": 226438,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 5237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115248474.495, "dur": 7344.718, + "args": { + "External id": 226439,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 5238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115248480.001, "dur": 4.992, + "args": { + "External id": 226440,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115248486.626, "dur": 7329.183, + "args": { + "External id": 226441,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 5240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115256035.438, "dur": 29.389, + "args": { + "External id": 226442,"Sequence number": 2757755, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 5241 + } + }, + { + "ph": "s", "id": 201, "pid": 4183440, "tid": 4183440, "ts": 667115256035.438, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115256050.741, "dur": 9.791, + "args": { + "External id": 226443,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 5242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115256055.699, "dur": 4.608, + "args": { + "External id": 226444,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 5243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115256129.491, "dur": 87.791, + "args": { + "External id": 226445,"Record function id": 0, "Ev Idx": 5244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115256218.715, "dur": 1127.142, + "args": { + "External id": 226446,"Record function id": 0, "Ev Idx": 5245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115256259.307, "dur": 1073.418, + "args": { + "External id": 226447,"Sequence number": 2757756, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 5246 + } + }, + { + "ph": "s", "id": 200, "pid": 4183440, "tid": 4183440, "ts": 667115256259.307, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115256328.561, "dur": 39.657, + "args": { + "External id": 226448,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115256379.970, "dur": 94.234, + "args": { + "External id": 226449,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115256483.150, "dur": 61.992, + "args": { + "External id": 226450,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115256556.584, "dur": 29.680, + "args": { + "External id": 226451,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115256615.112, "dur": 25.684, + "args": { + "External id": 226452,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115256705.418, "dur": 21.658, + "args": { + "External id": 226453,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115256757.760, "dur": 133.189, + "args": { + "External id": 226454,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 5253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115256809.838, "dur": 12.242, + "args": { + "External id": 226455,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 5254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115256814.484, "dur": 6.588, + "args": { + "External id": 226456,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115256826.607, "dur": 3.772, + "args": { + "External id": 226457,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115256831.416, "dur": 0.985, + "args": { + "External id": 226458,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115256834.554, "dur": 3.676, + "args": { + "External id": 226459,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115256901.857, "dur": 53.412, + "args": { + "External id": 226460,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115256989.289, "dur": 29.111, + "args": { + "External id": 226461,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115257026.364, "dur": 56.906, + "args": { + "External id": 226462,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115257091.498, "dur": 47.873, + "args": { + "External id": 226463,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115257161.122, "dur": 26.205, + "args": { + "External id": 226464,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 5263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115257193.066, "dur": 32.389, + "args": { + "External id": 226465,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 5264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115257245.915, "dur": 17.734, + "args": { + "External id": 226466,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 5265 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.5)", "pid": 4183440, "tid": 4183440, + "ts": 667115257409.754, "dur": 72.836, + "args": { + "External id": 226467,"Record function id": 0, "Ev Idx": 5266 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115257578.026, "dur": 47.146, + "args": { + "External id": 226468,"Record function id": 0, "Ev Idx": 5267 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.6)", "pid": 4183440, "tid": 4183440, + "ts": 667115257634.639, "dur": 9117.656, + "args": { + "External id": 226469,"Record function id": 0, "Ev Idx": 5268 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 4183440, "tid": 4183440, + "ts": 667115257645.955, "dur": 980.374, + "args": { + "External id": 226470,"Record function id": 0, "Ev Idx": 5269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115257767.044, "dur": 9.883, + "args": { + "External id": 226471,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115257791.954, "dur": 38.594, + "args": { + "External id": 226472,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257797.066, "dur": 2.245, + "args": { + "External id": 226473,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257803.345, "dur": 0.221, + "args": { + "External id": 226474,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257806.058, "dur": 0.449, + "args": { + "External id": 226475,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257807.296, "dur": 0.284, + "args": { + "External id": 226476,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257810.794, "dur": 0.368, + "args": { + "External id": 226477,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257813.793, "dur": 0.403, + "args": { + "External id": 226478,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257815.102, "dur": 3.522, + "args": { + "External id": 226479,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257821.083, "dur": 0.481, + "args": { + "External id": 226480,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257822.562, "dur": 0.157, + "args": { + "External id": 226481,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115257840.591, "dur": 44.867, + "args": { + "External id": 226482,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115257920.276, "dur": 112.399, + "args": { + "External id": 226483,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 5282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115257932.263, "dur": 3.585, + "args": { + "External id": 226484,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115257940.404, "dur": 9.675, + "args": { + "External id": 226485,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115257944.979, "dur": 4.677, + "args": { + "External id": 226486,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 5285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257947.945, "dur": 0.509, + "args": { + "External id": 226487,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115257956.402, "dur": 33.912, + "args": { + "External id": 226488,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257960.356, "dur": 2.868, + "args": { + "External id": 226489,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257964.004, "dur": 0.394, + "args": { + "External id": 226490,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257965.224, "dur": 0.176, + "args": { + "External id": 226491,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257970.718, "dur": 1.507, + "args": { + "External id": 226492,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257973.003, "dur": 0.205, + "args": { + "External id": 226493,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257975.666, "dur": 0.294, + "args": { + "External id": 226494,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257979.266, "dur": 0.358, + "args": { + "External id": 226495,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257980.249, "dur": 0.486, + "args": { + "External id": 226496,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115257983.286, "dur": 2.158, + "args": { + "External id": 226497,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115258001.623, "dur": 23.062, + "args": { + "External id": 226498,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115258084.098, "dur": 436.179, + "args": { + "External id": 226499,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 5298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115258115.271, "dur": 398.972, + "args": { + "External id": 226500,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5299, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115258125.158, "dur": 361.668, + "args": { + "External id": 226501,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 5300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115258545.907, "dur": 3.178, + "args": { + "External id": 226502,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5301, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 4183440, "tid": 4183440, + "ts": 667115258648.929, "dur": 7885.406, + "args": { + "External id": 226503,"Record function id": 0, "Ev Idx": 5302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115258788.707, "dur": 7.275, + "args": { + "External id": 226504,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 5303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115258799.683, "dur": 1.032, + "args": { + "External id": 226505,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115258802.241, "dur": 2.322, + "args": { + "External id": 226506,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115258806.146, "dur": 0.879, + "args": { + "External id": 226507,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115258808.370, "dur": 0.920, + "args": { + "External id": 226508,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115258810.498, "dur": 0.943, + "args": { + "External id": 226509,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115258816.148, "dur": 0.817, + "args": { + "External id": 226510,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115258818.396, "dur": 1.886, + "args": { + "External id": 226511,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115258822.074, "dur": 0.748, + "args": { + "External id": 226512,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115258824.699, "dur": 0.629, + "args": { + "External id": 226513,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115258846.449, "dur": 7633.517, + "args": { + "External id": 226514,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115258862.630, "dur": 7610.726, + "args": { + "External id": 226515,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115258880.101, "dur": 15.671, + "args": { + "External id": 226516,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115258898.399, "dur": 7541.544, + "args": { + "External id": 226517,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 5316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115258900.971, "dur": 7538.419, + "args": { + "External id": 226518,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 5317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115258907.760, "dur": 6.657, + "args": { + "External id": 226519,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115258916.036, "dur": 7520.198, + "args": { + "External id": 226520,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 5319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115266697.323, "dur": 29.362, + "args": { + "External id": 226521,"Sequence number": 2757757, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 5320 + } + }, + { + "ph": "s", "id": 199, "pid": 4183440, "tid": 4183440, "ts": 667115266697.323, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115266713.538, "dur": 8.280, + "args": { + "External id": 226522,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 5321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115266716.817, "dur": 4.652, + "args": { + "External id": 226523,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 5322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115266793.604, "dur": 91.359, + "args": { + "External id": 226524,"Record function id": 0, "Ev Idx": 5323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115266886.828, "dur": 1114.342, + "args": { + "External id": 226525,"Record function id": 0, "Ev Idx": 5324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115266929.061, "dur": 1058.096, + "args": { + "External id": 226526,"Sequence number": 2757758, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 5325 + } + }, + { + "ph": "s", "id": 198, "pid": 4183440, "tid": 4183440, "ts": 667115266929.061, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115266996.151, "dur": 45.287, + "args": { + "External id": 226527,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115267054.114, "dur": 94.648, + "args": { + "External id": 226528,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115267158.522, "dur": 35.324, + "args": { + "External id": 226529,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115267203.320, "dur": 28.858, + "args": { + "External id": 226530,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115267258.540, "dur": 27.392, + "args": { + "External id": 226531,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115267304.355, "dur": 15.799, + "args": { + "External id": 226532,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115267338.335, "dur": 130.483, + "args": { + "External id": 226533,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 5332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115267390.891, "dur": 10.548, + "args": { + "External id": 226534,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 5333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115267395.616, "dur": 5.037, + "args": { + "External id": 226535,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115267404.269, "dur": 6.076, + "args": { + "External id": 226536,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115267411.705, "dur": 0.896, + "args": { + "External id": 226537,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115267414.881, "dur": 3.850, + "args": { + "External id": 226538,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115267479.242, "dur": 67.842, + "args": { + "External id": 226539,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115267583.052, "dur": 29.806, + "args": { + "External id": 226540,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115267621.198, "dur": 72.786, + "args": { + "External id": 226541,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115267705.383, "dur": 54.258, + "args": { + "External id": 226542,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115267786.598, "dur": 31.511, + "args": { + "External id": 226543,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 5342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115267823.565, "dur": 48.006, + "args": { + "External id": 226544,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 5343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115267891.330, "dur": 20.735, + "args": { + "External id": 226545,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 5344 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.6)", "pid": 4183440, "tid": 4183440, + "ts": 667115268067.092, "dur": 74.145, + "args": { + "External id": 226546,"Record function id": 0, "Ev Idx": 5345 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115268212.451, "dur": 46.935, + "args": { + "External id": 226547,"Record function id": 0, "Ev Idx": 5346 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.7)", "pid": 4183440, "tid": 4183440, + "ts": 667115268268.549, "dur": 8709.655, + "args": { + "External id": 226548,"Record function id": 0, "Ev Idx": 5347 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 4183440, "tid": 4183440, + "ts": 667115268276.293, "dur": 937.904, + "args": { + "External id": 226549,"Record function id": 0, "Ev Idx": 5348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115268354.822, "dur": 8.279, + "args": { + "External id": 226550,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115268377.037, "dur": 40.520, + "args": { + "External id": 226551,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268382.846, "dur": 2.421, + "args": { + "External id": 226552,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268390.626, "dur": 0.252, + "args": { + "External id": 226553,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268392.853, "dur": 0.404, + "args": { + "External id": 226554,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268394.943, "dur": 0.395, + "args": { + "External id": 226555,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268398.527, "dur": 0.466, + "args": { + "External id": 226556,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268400.633, "dur": 0.326, + "args": { + "External id": 226557,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268402.434, "dur": 3.747, + "args": { + "External id": 226558,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268407.933, "dur": 0.363, + "args": { + "External id": 226559,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268409.732, "dur": 0.507, + "args": { + "External id": 226560,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115268427.918, "dur": 41.468, + "args": { + "External id": 226561,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115268522.837, "dur": 127.725, + "args": { + "External id": 226562,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 5361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115268537.180, "dur": 5.573, + "args": { + "External id": 226563,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115268548.202, "dur": 11.202, + "args": { + "External id": 226564,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115268552.672, "dur": 6.307, + "args": { + "External id": 226565,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 5364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268556.712, "dur": 0.680, + "args": { + "External id": 226566,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115268566.446, "dur": 34.111, + "args": { + "External id": 226567,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268569.097, "dur": 2.626, + "args": { + "External id": 226568,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268573.161, "dur": 0.367, + "args": { + "External id": 226569,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268575.213, "dur": 0.370, + "args": { + "External id": 226570,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268579.364, "dur": 1.525, + "args": { + "External id": 226571,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268582.505, "dur": 0.611, + "args": { + "External id": 226572,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268584.783, "dur": 0.163, + "args": { + "External id": 226573,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268588.676, "dur": 0.161, + "args": { + "External id": 226574,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268590.648, "dur": 0.176, + "args": { + "External id": 226575,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115268592.346, "dur": 2.636, + "args": { + "External id": 226576,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115268617.142, "dur": 25.782, + "args": { + "External id": 226577,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115268746.292, "dur": 374.190, + "args": { + "External id": 226578,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 5377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115268780.785, "dur": 334.856, + "args": { + "External id": 226579,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5378, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115268792.143, "dur": 318.113, + "args": { + "External id": 226580,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 5379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115269142.450, "dur": 2.290, + "args": { + "External id": 226581,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5380, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 4183440, "tid": 4183440, + "ts": 667115269234.742, "dur": 7555.324, + "args": { + "External id": 226582,"Record function id": 0, "Ev Idx": 5381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115269330.201, "dur": 6.408, + "args": { + "External id": 226583,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 5382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115269340.463, "dur": 1.151, + "args": { + "External id": 226584,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115269343.492, "dur": 2.108, + "args": { + "External id": 226585,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115269349.107, "dur": 1.069, + "args": { + "External id": 226586,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115269351.987, "dur": 1.045, + "args": { + "External id": 226587,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115269354.698, "dur": 0.865, + "args": { + "External id": 226588,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115269357.243, "dur": 1.225, + "args": { + "External id": 226589,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115269362.718, "dur": 2.280, + "args": { + "External id": 226590,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115269366.421, "dur": 0.683, + "args": { + "External id": 226591,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115269368.775, "dur": 0.623, + "args": { + "External id": 226592,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115269388.433, "dur": 7357.506, + "args": { + "External id": 226593,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115269404.213, "dur": 7334.808, + "args": { + "External id": 226594,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115269418.648, "dur": 14.583, + "args": { + "External id": 226595,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115269437.482, "dur": 7269.095, + "args": { + "External id": 226596,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 5395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115269439.772, "dur": 7266.141, + "args": { + "External id": 226597,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 5396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115269446.122, "dur": 6.379, + "args": { + "External id": 226598,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115269454.257, "dur": 7248.405, + "args": { + "External id": 226599,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 5398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115276924.465, "dur": 29.909, + "args": { + "External id": 226600,"Sequence number": 2757759, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 5399 + } + }, + { + "ph": "s", "id": 197, "pid": 4183440, "tid": 4183440, "ts": 667115276924.465, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115276941.905, "dur": 7.845, + "args": { + "External id": 226601,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 5400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115276945.281, "dur": 4.261, + "args": { + "External id": 226602,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 5401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115277016.634, "dur": 88.055, + "args": { + "External id": 226603,"Record function id": 0, "Ev Idx": 5402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115277106.544, "dur": 1107.068, + "args": { + "External id": 226604,"Record function id": 0, "Ev Idx": 5403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115277148.219, "dur": 1051.925, + "args": { + "External id": 226605,"Sequence number": 2757760, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 5404 + } + }, + { + "ph": "s", "id": 196, "pid": 4183440, "tid": 4183440, "ts": 667115277148.219, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115277214.722, "dur": 40.628, + "args": { + "External id": 226606,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115277269.013, "dur": 94.949, + "args": { + "External id": 226607,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115277373.102, "dur": 34.598, + "args": { + "External id": 226608,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115277417.410, "dur": 29.563, + "args": { + "External id": 226609,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115277469.564, "dur": 43.388, + "args": { + "External id": 226610,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115277535.590, "dur": 18.286, + "args": { + "External id": 226611,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115277571.368, "dur": 178.657, + "args": { + "External id": 226612,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 5411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115277618.696, "dur": 11.810, + "args": { + "External id": 226613,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 5412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115277623.762, "dur": 5.959, + "args": { + "External id": 226614,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115277633.237, "dur": 5.994, + "args": { + "External id": 226615,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115277648.607, "dur": 0.875, + "args": { + "External id": 226616,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115277687.429, "dur": 4.745, + "args": { + "External id": 226617,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115277762.478, "dur": 54.852, + "args": { + "External id": 226618,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115277850.016, "dur": 30.292, + "args": { + "External id": 226619,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115277889.325, "dur": 39.948, + "args": { + "External id": 226620,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115277937.699, "dur": 47.704, + "args": { + "External id": 226621,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115278007.489, "dur": 27.011, + "args": { + "External id": 226622,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 5421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115278039.811, "dur": 47.058, + "args": { + "External id": 226623,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 5422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115278107.900, "dur": 18.989, + "args": { + "External id": 226624,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 5423 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.7)", "pid": 4183440, "tid": 4183440, + "ts": 667115278278.055, "dur": 76.068, + "args": { + "External id": 226625,"Record function id": 0, "Ev Idx": 5424 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115278426.849, "dur": 47.399, + "args": { + "External id": 226626,"Record function id": 0, "Ev Idx": 5425 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.8)", "pid": 4183440, "tid": 4183440, + "ts": 667115278482.790, "dur": 8736.342, + "args": { + "External id": 226627,"Record function id": 0, "Ev Idx": 5426 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 4183440, "tid": 4183440, + "ts": 667115278489.868, "dur": 926.643, + "args": { + "External id": 226628,"Record function id": 0, "Ev Idx": 5427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115278592.821, "dur": 9.623, + "args": { + "External id": 226629,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115278616.104, "dur": 74.380, + "args": { + "External id": 226630,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278621.847, "dur": 2.275, + "args": { + "External id": 226631,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278628.763, "dur": 0.378, + "args": { + "External id": 226632,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278630.940, "dur": 0.381, + "args": { + "External id": 226633,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278632.580, "dur": 0.604, + "args": { + "External id": 226634,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278636.948, "dur": 0.239, + "args": { + "External id": 226635,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278638.886, "dur": 0.353, + "args": { + "External id": 226636,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278640.779, "dur": 3.224, + "args": { + "External id": 226637,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278645.537, "dur": 0.455, + "args": { + "External id": 226638,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278647.395, "dur": 0.245, + "args": { + "External id": 226639,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115278704.154, "dur": 43.774, + "args": { + "External id": 226640,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115278784.567, "dur": 116.621, + "args": { + "External id": 226641,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 5440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115278797.836, "dur": 5.089, + "args": { + "External id": 226642,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115278807.644, "dur": 10.926, + "args": { + "External id": 226643,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115278812.071, "dur": 6.058, + "args": { + "External id": 226644,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 5443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278816.054, "dur": 0.680, + "args": { + "External id": 226645,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115278825.785, "dur": 31.987, + "args": { + "External id": 226646,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278828.009, "dur": 2.679, + "args": { + "External id": 226647,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278832.470, "dur": 0.331, + "args": { + "External id": 226648,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278834.359, "dur": 0.245, + "args": { + "External id": 226649,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278838.363, "dur": 1.062, + "args": { + "External id": 226650,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278840.903, "dur": 0.168, + "args": { + "External id": 226651,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278842.804, "dur": 0.286, + "args": { + "External id": 226652,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278846.370, "dur": 0.248, + "args": { + "External id": 226653,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278848.096, "dur": 0.205, + "args": { + "External id": 226654,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115278849.630, "dur": 2.328, + "args": { + "External id": 226655,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115278870.569, "dur": 23.086, + "args": { + "External id": 226656,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115278956.377, "dur": 371.831, + "args": { + "External id": 226657,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 5456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115278987.533, "dur": 335.431, + "args": { + "External id": 226658,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5457, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115278998.301, "dur": 316.625, + "args": { + "External id": 226659,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 5458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115279350.091, "dur": 2.193, + "args": { + "External id": 226660,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5459, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 4183440, "tid": 4183440, + "ts": 667115279436.523, "dur": 7594.547, + "args": { + "External id": 226661,"Record function id": 0, "Ev Idx": 5460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115279547.391, "dur": 6.712, + "args": { + "External id": 226662,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 5461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115279558.080, "dur": 0.933, + "args": { + "External id": 226663,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115279561.145, "dur": 2.465, + "args": { + "External id": 226664,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115279565.685, "dur": 1.091, + "args": { + "External id": 226665,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115279568.536, "dur": 0.848, + "args": { + "External id": 226666,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115279570.760, "dur": 0.915, + "args": { + "External id": 226667,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115279574.930, "dur": 0.869, + "args": { + "External id": 226668,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115279577.411, "dur": 2.074, + "args": { + "External id": 226669,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115279581.022, "dur": 0.764, + "args": { + "External id": 226670,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115279583.216, "dur": 0.874, + "args": { + "External id": 226671,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115279616.825, "dur": 7368.467, + "args": { + "External id": 226672,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115279633.129, "dur": 7345.096, + "args": { + "External id": 226673,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115279649.484, "dur": 53.567, + "args": { + "External id": 226674,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115279706.746, "dur": 7238.676, + "args": { + "External id": 226675,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 5474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115279709.056, "dur": 7235.792, + "args": { + "External id": 226676,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 5475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115279715.274, "dur": 7.196, + "args": { + "External id": 226677,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115279724.123, "dur": 7217.426, + "args": { + "External id": 226678,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 5477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115287165.505, "dur": 29.546, + "args": { + "External id": 226679,"Sequence number": 2757761, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 5478 + } + }, + { + "ph": "s", "id": 195, "pid": 4183440, "tid": 4183440, "ts": 667115287165.505, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115287182.571, "dur": 7.868, + "args": { + "External id": 226680,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 5479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115287186.010, "dur": 4.241, + "args": { + "External id": 226681,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 5480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115287257.918, "dur": 88.488, + "args": { + "External id": 226682,"Record function id": 0, "Ev Idx": 5481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115287348.272, "dur": 1065.779, + "args": { + "External id": 226683,"Record function id": 0, "Ev Idx": 5482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115287390.078, "dur": 1010.413, + "args": { + "External id": 226684,"Sequence number": 2757762, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 5483 + } + }, + { + "ph": "s", "id": 194, "pid": 4183440, "tid": 4183440, "ts": 667115287390.078, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115287458.645, "dur": 60.337, + "args": { + "External id": 226685,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115287534.253, "dur": 92.642, + "args": { + "External id": 226686,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115287636.175, "dur": 70.628, + "args": { + "External id": 226687,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115287721.367, "dur": 32.633, + "args": { + "External id": 226688,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115287780.988, "dur": 25.061, + "args": { + "External id": 226689,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115287822.668, "dur": 16.025, + "args": { + "External id": 226690,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115287858.383, "dur": 126.696, + "args": { + "External id": 226691,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 5490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115287908.066, "dur": 11.669, + "args": { + "External id": 226692,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 5491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115287913.319, "dur": 5.391, + "args": { + "External id": 226693,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115287922.515, "dur": 6.532, + "args": { + "External id": 226694,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115287930.489, "dur": 0.919, + "args": { + "External id": 226695,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115287933.624, "dur": 3.717, + "args": { + "External id": 226696,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115287995.614, "dur": 45.362, + "args": { + "External id": 226697,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115288070.098, "dur": 28.004, + "args": { + "External id": 226698,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115288106.702, "dur": 37.573, + "args": { + "External id": 226699,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115288152.827, "dur": 31.378, + "args": { + "External id": 226700,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115288208.757, "dur": 26.245, + "args": { + "External id": 226701,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 5500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115288240.711, "dur": 45.216, + "args": { + "External id": 226702,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 5501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115288305.210, "dur": 18.088, + "args": { + "External id": 226703,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 5502 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.8)", "pid": 4183440, "tid": 4183440, + "ts": 667115288476.961, "dur": 94.679, + "args": { + "External id": 226704,"Record function id": 0, "Ev Idx": 5503 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115288646.161, "dur": 87.021, + "args": { + "External id": 226705,"Record function id": 0, "Ev Idx": 5504 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.9)", "pid": 4183440, "tid": 4183440, + "ts": 667115288743.252, "dur": 8726.541, + "args": { + "External id": 226706,"Record function id": 0, "Ev Idx": 5505 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 4183440, "tid": 4183440, + "ts": 667115288752.159, "dur": 940.294, + "args": { + "External id": 226707,"Record function id": 0, "Ev Idx": 5506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115288832.835, "dur": 9.851, + "args": { + "External id": 226708,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115288857.486, "dur": 40.657, + "args": { + "External id": 226709,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115288863.627, "dur": 2.480, + "args": { + "External id": 226710,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115288871.463, "dur": 0.437, + "args": { + "External id": 226711,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115288873.604, "dur": 0.527, + "args": { + "External id": 226712,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115288875.541, "dur": 0.201, + "args": { + "External id": 226713,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115288879.170, "dur": 0.451, + "args": { + "External id": 226714,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115288881.520, "dur": 0.335, + "args": { + "External id": 226715,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115288883.221, "dur": 3.716, + "args": { + "External id": 226716,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115288888.622, "dur": 0.514, + "args": { + "External id": 226717,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115288890.533, "dur": 0.446, + "args": { + "External id": 226718,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115288908.462, "dur": 43.091, + "args": { + "External id": 226719,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115288985.528, "dur": 121.629, + "args": { + "External id": 226720,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 5519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115288995.278, "dur": 3.816, + "args": { + "External id": 226721,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115289003.693, "dur": 10.654, + "args": { + "External id": 226722,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115289008.346, "dur": 5.544, + "args": { + "External id": 226723,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 5522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115289012.083, "dur": 0.652, + "args": { + "External id": 226724,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115289021.410, "dur": 33.533, + "args": { + "External id": 226725,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115289023.504, "dur": 2.838, + "args": { + "External id": 226726,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115289030.911, "dur": 0.432, + "args": { + "External id": 226727,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115289032.692, "dur": 0.401, + "args": { + "External id": 226728,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115289036.799, "dur": 1.771, + "args": { + "External id": 226729,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115289039.957, "dur": 0.362, + "args": { + "External id": 226730,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115289041.578, "dur": 1.964, + "args": { + "External id": 226731,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115289045.018, "dur": 0.156, + "args": { + "External id": 226732,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115289046.577, "dur": 0.144, + "args": { + "External id": 226733,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115289050.361, "dur": 0.153, + "args": { + "External id": 226734,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115289074.982, "dur": 23.918, + "args": { + "External id": 226735,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115289158.776, "dur": 398.383, + "args": { + "External id": 226736,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 5535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115289191.067, "dur": 360.350, + "args": { + "External id": 226737,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5536, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115289203.653, "dur": 342.346, + "args": { + "External id": 226738,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 5537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115289581.191, "dur": 2.822, + "args": { + "External id": 226739,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5538, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 4183440, "tid": 4183440, + "ts": 667115289718.756, "dur": 7559.248, + "args": { + "External id": 226740,"Record function id": 0, "Ev Idx": 5539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115289822.472, "dur": 6.683, + "args": { + "External id": 226741,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 5540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115289832.861, "dur": 1.025, + "args": { + "External id": 226742,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115289835.752, "dur": 2.512, + "args": { + "External id": 226743,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115289839.950, "dur": 1.216, + "args": { + "External id": 226744,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115289842.748, "dur": 0.941, + "args": { + "External id": 226745,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115289847.401, "dur": 1.156, + "args": { + "External id": 226746,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115289849.956, "dur": 0.660, + "args": { + "External id": 226747,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115289852.119, "dur": 2.006, + "args": { + "External id": 226748,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115289855.645, "dur": 0.878, + "args": { + "External id": 226749,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115289859.857, "dur": 0.770, + "args": { + "External id": 226750,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115289879.276, "dur": 7354.493, + "args": { + "External id": 226751,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115289896.471, "dur": 7330.354, + "args": { + "External id": 226752,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115289911.883, "dur": 15.015, + "args": { + "External id": 226753,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115289929.481, "dur": 7264.924, + "args": { + "External id": 226754,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 5553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115289931.877, "dur": 7262.066, + "args": { + "External id": 226755,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 5554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115289937.768, "dur": 7.267, + "args": { + "External id": 226756,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115289947.071, "dur": 7243.740, + "args": { + "External id": 226757,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 5556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115297414.761, "dur": 29.291, + "args": { + "External id": 226758,"Sequence number": 2757763, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 5557 + } + }, + { + "ph": "s", "id": 193, "pid": 4183440, "tid": 4183440, "ts": 667115297414.761, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115297431.389, "dur": 7.800, + "args": { + "External id": 226759,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 5558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115297434.498, "dur": 4.450, + "args": { + "External id": 226760,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 5559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115297523.704, "dur": 90.615, + "args": { + "External id": 226761,"Record function id": 0, "Ev Idx": 5560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115297616.775, "dur": 1086.297, + "args": { + "External id": 226762,"Record function id": 0, "Ev Idx": 5561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115297687.482, "dur": 999.726, + "args": { + "External id": 226763,"Sequence number": 2757764, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 5562 + } + }, + { + "ph": "s", "id": 192, "pid": 4183440, "tid": 4183440, "ts": 667115297687.482, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115297755.306, "dur": 42.707, + "args": { + "External id": 226764,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115297811.732, "dur": 94.849, + "args": { + "External id": 226765,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115297916.475, "dur": 34.743, + "args": { + "External id": 226766,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115297959.933, "dur": 29.190, + "args": { + "External id": 226767,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115298014.221, "dur": 26.840, + "args": { + "External id": 226768,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115298059.202, "dur": 14.547, + "args": { + "External id": 226769,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115298091.927, "dur": 126.505, + "args": { + "External id": 226770,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 5569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115298140.776, "dur": 11.239, + "args": { + "External id": 226771,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 5570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115298145.764, "dur": 5.502, + "args": { + "External id": 226772,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115298154.835, "dur": 5.742, + "args": { + "External id": 226773,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115298161.937, "dur": 1.275, + "args": { + "External id": 226774,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115298165.518, "dur": 3.897, + "args": { + "External id": 226775,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115298228.617, "dur": 42.784, + "args": { + "External id": 226776,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115298300.637, "dur": 27.688, + "args": { + "External id": 226777,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115298344.709, "dur": 38.924, + "args": { + "External id": 226778,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115298392.580, "dur": 31.284, + "args": { + "External id": 226779,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115298448.732, "dur": 24.259, + "args": { + "External id": 226780,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 5579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115298478.476, "dur": 61.464, + "args": { + "External id": 226781,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 5580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115298563.938, "dur": 20.554, + "args": { + "External id": 226782,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 5581 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.9)", "pid": 4183440, "tid": 4183440, + "ts": 667115298769.480, "dur": 76.158, + "args": { + "External id": 226783,"Record function id": 0, "Ev Idx": 5582 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115298918.203, "dur": 47.906, + "args": { + "External id": 226784,"Record function id": 0, "Ev Idx": 5583 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.10)", "pid": 4183440, "tid": 4183440, + "ts": 667115298975.254, "dur": 9113.561, + "args": { + "External id": 226785,"Record function id": 0, "Ev Idx": 5584 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 4183440, "tid": 4183440, + "ts": 667115298982.811, "dur": 931.602, + "args": { + "External id": 226786,"Record function id": 0, "Ev Idx": 5585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115299059.675, "dur": 9.245, + "args": { + "External id": 226787,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115299082.007, "dur": 37.746, + "args": { + "External id": 226788,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299087.785, "dur": 2.456, + "args": { + "External id": 226789,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299095.260, "dur": 0.462, + "args": { + "External id": 226790,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299097.101, "dur": 0.315, + "args": { + "External id": 226791,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299098.892, "dur": 0.331, + "args": { + "External id": 226792,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299102.587, "dur": 0.366, + "args": { + "External id": 226793,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299104.618, "dur": 0.474, + "args": { + "External id": 226794,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299106.229, "dur": 3.649, + "args": { + "External id": 226795,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299111.026, "dur": 0.200, + "args": { + "External id": 226796,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299112.295, "dur": 0.454, + "args": { + "External id": 226797,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115299130.471, "dur": 42.587, + "args": { + "External id": 226798,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115299206.349, "dur": 109.227, + "args": { + "External id": 226799,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 5598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115299216.840, "dur": 4.782, + "args": { + "External id": 226800,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115299226.641, "dur": 10.985, + "args": { + "External id": 226801,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115299231.171, "dur": 5.963, + "args": { + "External id": 226802,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 5601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299235.107, "dur": 0.715, + "args": { + "External id": 226803,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115299244.465, "dur": 29.414, + "args": { + "External id": 226804,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299246.161, "dur": 2.503, + "args": { + "External id": 226805,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299249.915, "dur": 0.431, + "args": { + "External id": 226806,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299251.647, "dur": 0.573, + "args": { + "External id": 226807,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299255.626, "dur": 1.699, + "args": { + "External id": 226808,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299258.613, "dur": 0.251, + "args": { + "External id": 226809,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299260.343, "dur": 0.288, + "args": { + "External id": 226810,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299263.541, "dur": 0.180, + "args": { + "External id": 226811,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299264.911, "dur": 0.451, + "args": { + "External id": 226812,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115299266.864, "dur": 2.208, + "args": { + "External id": 226813,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115299284.635, "dur": 22.988, + "args": { + "External id": 226814,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115299364.792, "dur": 449.235, + "args": { + "External id": 226815,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 5614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115299393.759, "dur": 413.533, + "args": { + "External id": 226816,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5615, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115299434.016, "dur": 367.836, + "args": { + "External id": 226817,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 5616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115299837.898, "dur": 2.527, + "args": { + "External id": 226818,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5617, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 4183440, "tid": 4183440, + "ts": 667115299935.438, "dur": 7968.441, + "args": { + "External id": 226819,"Record function id": 0, "Ev Idx": 5618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115300037.593, "dur": 6.409, + "args": { + "External id": 226820,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 5619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115300047.602, "dur": 1.135, + "args": { + "External id": 226821,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115300050.412, "dur": 2.543, + "args": { + "External id": 226822,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115300054.438, "dur": 0.798, + "args": { + "External id": 226823,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115300056.517, "dur": 1.051, + "args": { + "External id": 226824,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115300059.433, "dur": 0.770, + "args": { + "External id": 226825,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115300061.879, "dur": 1.107, + "args": { + "External id": 226826,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115300064.496, "dur": 1.996, + "args": { + "External id": 226827,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115300067.879, "dur": 1.011, + "args": { + "External id": 226828,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115300070.336, "dur": 0.910, + "args": { + "External id": 226829,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115300089.507, "dur": 7771.535, + "args": { + "External id": 226830,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115300106.066, "dur": 7748.375, + "args": { + "External id": 226831,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115300121.006, "dur": 15.230, + "args": { + "External id": 226832,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115300139.134, "dur": 7682.279, + "args": { + "External id": 226833,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 5632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115300141.799, "dur": 7678.933, + "args": { + "External id": 226834,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 5633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115300148.045, "dur": 7.175, + "args": { + "External id": 226835,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115300157.217, "dur": 7660.270, + "args": { + "External id": 226836,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 5635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115308035.894, "dur": 27.930, + "args": { + "External id": 226837,"Sequence number": 2757765, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 5636 + } + }, + { + "ph": "s", "id": 191, "pid": 4183440, "tid": 4183440, "ts": 667115308035.894, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115308051.466, "dur": 7.798, + "args": { + "External id": 226838,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 5637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115308054.541, "dur": 4.512, + "args": { + "External id": 226839,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 5638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115308128.652, "dur": 89.874, + "args": { + "External id": 226840,"Record function id": 0, "Ev Idx": 5639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115308220.368, "dur": 1095.684, + "args": { + "External id": 226841,"Record function id": 0, "Ev Idx": 5640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115308259.152, "dur": 1043.358, + "args": { + "External id": 226842,"Sequence number": 2757766, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 5641 + } + }, + { + "ph": "s", "id": 190, "pid": 4183440, "tid": 4183440, "ts": 667115308259.152, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115308322.379, "dur": 41.853, + "args": { + "External id": 226843,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115308377.565, "dur": 94.472, + "args": { + "External id": 226844,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115308481.613, "dur": 57.159, + "args": { + "External id": 226845,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115308549.232, "dur": 30.027, + "args": { + "External id": 226846,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115308604.054, "dur": 26.214, + "args": { + "External id": 226847,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115308647.376, "dur": 52.693, + "args": { + "External id": 226848,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115308721.424, "dur": 129.293, + "args": { + "External id": 226849,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 5648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115308772.643, "dur": 11.976, + "args": { + "External id": 226850,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 5649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115308777.466, "dur": 6.333, + "args": { + "External id": 226851,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115308786.966, "dur": 5.979, + "args": { + "External id": 226852,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115308794.240, "dur": 1.159, + "args": { + "External id": 226853,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115308797.571, "dur": 4.539, + "args": { + "External id": 226854,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115308862.033, "dur": 53.028, + "args": { + "External id": 226855,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115308945.859, "dur": 32.665, + "args": { + "External id": 226856,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115308987.231, "dur": 37.310, + "args": { + "External id": 226857,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115309033.417, "dur": 49.921, + "args": { + "External id": 226858,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115309105.744, "dur": 23.373, + "args": { + "External id": 226859,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 5658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115309134.896, "dur": 50.711, + "args": { + "External id": 226860,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 5659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115309205.532, "dur": 19.027, + "args": { + "External id": 226861,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 5660 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.10)", "pid": 4183440, "tid": 4183440, + "ts": 667115309378.760, "dur": 77.528, + "args": { + "External id": 226862,"Record function id": 0, "Ev Idx": 5661 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115309548.767, "dur": 48.239, + "args": { + "External id": 226863,"Record function id": 0, "Ev Idx": 5662 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.11)", "pid": 4183440, "tid": 4183440, + "ts": 667115309605.426, "dur": 8924.779, + "args": { + "External id": 226864,"Record function id": 0, "Ev Idx": 5663 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 4183440, "tid": 4183440, + "ts": 667115309613.559, "dur": 958.436, + "args": { + "External id": 226865,"Record function id": 0, "Ev Idx": 5664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115309736.816, "dur": 10.282, + "args": { + "External id": 226866,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115309761.017, "dur": 35.838, + "args": { + "External id": 226867,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309766.747, "dur": 2.275, + "args": { + "External id": 226868,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309773.564, "dur": 0.264, + "args": { + "External id": 226869,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309774.920, "dur": 0.517, + "args": { + "External id": 226870,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309776.590, "dur": 0.461, + "args": { + "External id": 226871,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309779.943, "dur": 0.508, + "args": { + "External id": 226872,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309781.432, "dur": 0.513, + "args": { + "External id": 226873,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309782.657, "dur": 4.221, + "args": { + "External id": 226874,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309788.089, "dur": 0.260, + "args": { + "External id": 226875,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309789.519, "dur": 0.184, + "args": { + "External id": 226876,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115309812.675, "dur": 46.112, + "args": { + "External id": 226877,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115309893.226, "dur": 115.180, + "args": { + "External id": 226878,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 5677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115309903.573, "dur": 6.755, + "args": { + "External id": 226879,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115309915.261, "dur": 11.442, + "args": { + "External id": 226880,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115309920.107, "dur": 6.119, + "args": { + "External id": 226881,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 5680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309923.964, "dur": 0.596, + "args": { + "External id": 226882,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115309933.705, "dur": 31.012, + "args": { + "External id": 226883,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309935.910, "dur": 0.242, + "args": { + "External id": 226884,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309937.973, "dur": 2.528, + "args": { + "External id": 226885,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309941.883, "dur": 0.564, + "args": { + "External id": 226886,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309944.694, "dur": 1.511, + "args": { + "External id": 226887,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309949.452, "dur": 0.416, + "args": { + "External id": 226888,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309951.484, "dur": 0.355, + "args": { + "External id": 226889,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309953.248, "dur": 0.447, + "args": { + "External id": 226890,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309957.393, "dur": 0.166, + "args": { + "External id": 226891,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115309959.090, "dur": 0.288, + "args": { + "External id": 226892,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115309976.645, "dur": 24.153, + "args": { + "External id": 226893,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115310064.428, "dur": 394.695, + "args": { + "External id": 226894,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 5693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115310093.334, "dur": 360.735, + "args": { + "External id": 226895,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5694, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115310104.823, "dur": 344.067, + "args": { + "External id": 226896,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 5695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115310478.761, "dur": 2.369, + "args": { + "External id": 226897,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5696, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 4183440, "tid": 4183440, + "ts": 667115310594.622, "dur": 7735.846, + "args": { + "External id": 226898,"Record function id": 0, "Ev Idx": 5697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115310727.975, "dur": 7.120, + "args": { + "External id": 226899,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 5698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115310738.696, "dur": 1.107, + "args": { + "External id": 226900,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115310741.527, "dur": 2.356, + "args": { + "External id": 226901,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115310745.380, "dur": 0.815, + "args": { + "External id": 226902,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115310748.268, "dur": 0.864, + "args": { + "External id": 226903,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115310750.530, "dur": 0.892, + "args": { + "External id": 226904,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115310753.311, "dur": 1.015, + "args": { + "External id": 226905,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115310756.119, "dur": 2.398, + "args": { + "External id": 226906,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115310760.352, "dur": 0.646, + "args": { + "External id": 226907,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115310762.645, "dur": 0.844, + "args": { + "External id": 226908,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115310783.701, "dur": 7508.277, + "args": { + "External id": 226909,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115310800.620, "dur": 7484.552, + "args": { + "External id": 226910,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115310818.452, "dur": 15.952, + "args": { + "External id": 226911,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115310837.177, "dur": 7416.559, + "args": { + "External id": 226912,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 5711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115310839.927, "dur": 7413.237, + "args": { + "External id": 226913,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 5712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115310846.145, "dur": 6.632, + "args": { + "External id": 226914,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115310855.235, "dur": 7394.893, + "args": { + "External id": 226915,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 5714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115318456.419, "dur": 46.805, + "args": { + "External id": 226916,"Sequence number": 2757767, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 5715 + } + }, + { + "ph": "s", "id": 189, "pid": 4183440, "tid": 4183440, "ts": 667115318456.419, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115318478.812, "dur": 8.074, + "args": { + "External id": 226917,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 5716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115318482.478, "dur": 4.226, + "args": { + "External id": 226918,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 5717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115318571.623, "dur": 119.549, + "args": { + "External id": 226919,"Record function id": 0, "Ev Idx": 5718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115318694.410, "dur": 1066.015, + "args": { + "External id": 226920,"Record function id": 0, "Ev Idx": 5719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115318737.622, "dur": 1007.258, + "args": { + "External id": 226921,"Sequence number": 2757768, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 5720 + } + }, + { + "ph": "s", "id": 188, "pid": 4183440, "tid": 4183440, "ts": 667115318737.622, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115318809.171, "dur": 44.516, + "args": { + "External id": 226922,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115318866.613, "dur": 92.552, + "args": { + "External id": 226923,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115318968.889, "dur": 34.008, + "args": { + "External id": 226924,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115319012.015, "dur": 28.991, + "args": { + "External id": 226925,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115319064.796, "dur": 26.786, + "args": { + "External id": 226926,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115319107.882, "dur": 15.673, + "args": { + "External id": 226927,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115319142.034, "dur": 126.736, + "args": { + "External id": 226928,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 5727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115319188.702, "dur": 11.857, + "args": { + "External id": 226929,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 5728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115319194.012, "dur": 5.732, + "args": { + "External id": 226930,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115319203.511, "dur": 5.060, + "args": { + "External id": 226931,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115319209.719, "dur": 1.117, + "args": { + "External id": 226932,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115319213.241, "dur": 4.487, + "args": { + "External id": 226933,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115319279.807, "dur": 44.238, + "args": { + "External id": 226934,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115319353.627, "dur": 28.787, + "args": { + "External id": 226935,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115319390.596, "dur": 37.284, + "args": { + "External id": 226936,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115319435.939, "dur": 31.620, + "args": { + "External id": 226937,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115319489.338, "dur": 45.231, + "args": { + "External id": 226938,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 5737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115319541.556, "dur": 50.991, + "args": { + "External id": 226939,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 5738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115319613.862, "dur": 19.929, + "args": { + "External id": 226940,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 5739 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.11)", "pid": 4183440, "tid": 4183440, + "ts": 667115319827.769, "dur": 77.713, + "args": { + "External id": 226941,"Record function id": 0, "Ev Idx": 5740 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115319976.528, "dur": 47.354, + "args": { + "External id": 226942,"Record function id": 0, "Ev Idx": 5741 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.12)", "pid": 4183440, "tid": 4183440, + "ts": 667115320032.791, "dur": 8799.323, + "args": { + "External id": 226943,"Record function id": 0, "Ev Idx": 5742 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 4183440, "tid": 4183440, + "ts": 667115320040.763, "dur": 913.886, + "args": { + "External id": 226944,"Record function id": 0, "Ev Idx": 5743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115320122.201, "dur": 9.522, + "args": { + "External id": 226945,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115320147.532, "dur": 40.373, + "args": { + "External id": 226946,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320153.374, "dur": 2.053, + "args": { + "External id": 226947,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320159.730, "dur": 0.570, + "args": { + "External id": 226948,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320161.961, "dur": 0.513, + "args": { + "External id": 226949,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320164.485, "dur": 2.111, + "args": { + "External id": 226950,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320168.284, "dur": 0.473, + "args": { + "External id": 226951,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320170.029, "dur": 0.623, + "args": { + "External id": 226952,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320175.238, "dur": 1.693, + "args": { + "External id": 226953,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320178.459, "dur": 0.303, + "args": { + "External id": 226954,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320180.222, "dur": 0.331, + "args": { + "External id": 226955,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115320199.234, "dur": 42.450, + "args": { + "External id": 226956,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115320274.691, "dur": 112.065, + "args": { + "External id": 226957,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 5756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115320285.490, "dur": 3.951, + "args": { + "External id": 226958,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115320294.250, "dur": 12.809, + "args": { + "External id": 226959,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115320298.828, "dur": 7.757, + "args": { + "External id": 226960,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 5759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320302.901, "dur": 2.442, + "args": { + "External id": 226961,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115320313.382, "dur": 31.262, + "args": { + "External id": 226962,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320315.797, "dur": 0.251, + "args": { + "External id": 226963,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320317.753, "dur": 0.496, + "args": { + "External id": 226964,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320319.870, "dur": 0.353, + "args": { + "External id": 226965,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320323.395, "dur": 1.942, + "args": { + "External id": 226966,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320327.110, "dur": 0.482, + "args": { + "External id": 226967,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320329.404, "dur": 2.703, + "args": { + "External id": 226968,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320334.085, "dur": 0.469, + "args": { + "External id": 226969,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320335.983, "dur": 0.515, + "args": { + "External id": 226970,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115320340.134, "dur": 0.200, + "args": { + "External id": 226971,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115320355.590, "dur": 23.919, + "args": { + "External id": 226972,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115320438.696, "dur": 415.094, + "args": { + "External id": 226973,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 5772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115320466.012, "dur": 381.830, + "args": { + "External id": 226974,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5773, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115320476.596, "dur": 365.208, + "args": { + "External id": 226975,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 5774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115320878.301, "dur": 2.636, + "args": { + "External id": 226976,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5775, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 4183440, "tid": 4183440, + "ts": 667115320975.549, "dur": 7636.212, + "args": { + "External id": 226977,"Record function id": 0, "Ev Idx": 5776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115321073.845, "dur": 6.734, + "args": { + "External id": 226978,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 5777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115321083.715, "dur": 1.197, + "args": { + "External id": 226979,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115321086.591, "dur": 2.163, + "args": { + "External id": 226980,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115321090.271, "dur": 0.998, + "args": { + "External id": 226981,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115321093.215, "dur": 0.824, + "args": { + "External id": 226982,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115321095.763, "dur": 1.032, + "args": { + "External id": 226983,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115321098.889, "dur": 0.843, + "args": { + "External id": 226984,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115321101.906, "dur": 2.350, + "args": { + "External id": 226985,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115321106.018, "dur": 0.793, + "args": { + "External id": 226986,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115321108.675, "dur": 0.688, + "args": { + "External id": 226987,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115321127.423, "dur": 7444.927, + "args": { + "External id": 226988,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115321143.425, "dur": 7422.042, + "args": { + "External id": 226989,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115321159.657, "dur": 15.558, + "args": { + "External id": 226990,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115321178.246, "dur": 7353.840, + "args": { + "External id": 226991,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 5790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115321180.816, "dur": 7350.790, + "args": { + "External id": 226992,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 5791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115321186.792, "dur": 7.184, + "args": { + "External id": 226993,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115321196.354, "dur": 7332.238, + "args": { + "External id": 226994,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 5793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115328770.706, "dur": 34.997, + "args": { + "External id": 226995,"Sequence number": 2757769, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 5794 + } + }, + { + "ph": "s", "id": 187, "pid": 4183440, "tid": 4183440, "ts": 667115328770.706, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115328792.513, "dur": 8.532, + "args": { + "External id": 226996,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 5795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115328796.227, "dur": 4.554, + "args": { + "External id": 226997,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 5796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115328870.817, "dur": 89.306, + "args": { + "External id": 226998,"Record function id": 0, "Ev Idx": 5797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115328961.637, "dur": 1091.459, + "args": { + "External id": 226999,"Record function id": 0, "Ev Idx": 5798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115329001.318, "dur": 1038.479, + "args": { + "External id": 227000,"Sequence number": 2757770, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 5799 + } + }, + { + "ph": "s", "id": 186, "pid": 4183440, "tid": 4183440, "ts": 667115329001.318, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115329066.322, "dur": 43.032, + "args": { + "External id": 227001,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115329122.166, "dur": 91.808, + "args": { + "External id": 227002,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115329223.327, "dur": 34.251, + "args": { + "External id": 227003,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115329265.799, "dur": 28.868, + "args": { + "External id": 227004,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115329318.090, "dur": 27.508, + "args": { + "External id": 227005,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115329363.194, "dur": 14.787, + "args": { + "External id": 227006,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115329395.500, "dur": 150.598, + "args": { + "External id": 227007,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 5806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115329443.559, "dur": 11.862, + "args": { + "External id": 227008,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 5807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115329448.601, "dur": 6.031, + "args": { + "External id": 227009,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115329458.461, "dur": 5.860, + "args": { + "External id": 227010,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115329465.961, "dur": 1.203, + "args": { + "External id": 227011,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115329469.827, "dur": 3.945, + "args": { + "External id": 227012,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115329558.386, "dur": 51.103, + "args": { + "External id": 227013,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115329640.184, "dur": 65.883, + "args": { + "External id": 227014,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115329718.470, "dur": 42.334, + "args": { + "External id": 227015,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115329770.096, "dur": 47.572, + "args": { + "External id": 227016,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115329847.911, "dur": 27.693, + "args": { + "External id": 227017,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 5816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115329883.771, "dur": 48.439, + "args": { + "External id": 227018,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 5817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115329949.806, "dur": 20.485, + "args": { + "External id": 227019,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 5818 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.12)", "pid": 4183440, "tid": 4183440, + "ts": 667115330117.680, "dur": 74.333, + "args": { + "External id": 227020,"Record function id": 0, "Ev Idx": 5819 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115330263.634, "dur": 45.640, + "args": { + "External id": 227021,"Record function id": 0, "Ev Idx": 5820 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.13)", "pid": 4183440, "tid": 4183440, + "ts": 667115330317.525, "dur": 9057.413, + "args": { + "External id": 227022,"Record function id": 0, "Ev Idx": 5821 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 4183440, "tid": 4183440, + "ts": 667115330326.430, "dur": 898.964, + "args": { + "External id": 227023,"Record function id": 0, "Ev Idx": 5822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115330404.867, "dur": 8.773, + "args": { + "External id": 227024,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115330426.829, "dur": 37.985, + "args": { + "External id": 227025,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330432.417, "dur": 2.280, + "args": { + "External id": 227026,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330439.540, "dur": 0.255, + "args": { + "External id": 227027,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330441.368, "dur": 0.227, + "args": { + "External id": 227028,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330443.094, "dur": 0.398, + "args": { + "External id": 227029,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330446.871, "dur": 0.360, + "args": { + "External id": 227030,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330448.743, "dur": 0.473, + "args": { + "External id": 227031,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330450.714, "dur": 3.791, + "args": { + "External id": 227032,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330456.302, "dur": 0.309, + "args": { + "External id": 227033,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330458.409, "dur": 0.162, + "args": { + "External id": 227034,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115330477.000, "dur": 58.000, + "args": { + "External id": 227035,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115330571.030, "dur": 158.075, + "args": { + "External id": 227036,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 5835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115330582.038, "dur": 5.637, + "args": { + "External id": 227037,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115330592.899, "dur": 11.112, + "args": { + "External id": 227038,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115330597.566, "dur": 5.989, + "args": { + "External id": 227039,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 5838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330601.299, "dur": 0.792, + "args": { + "External id": 227040,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115330611.122, "dur": 32.013, + "args": { + "External id": 227041,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330613.324, "dur": 2.174, + "args": { + "External id": 227042,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330617.383, "dur": 0.217, + "args": { + "External id": 227043,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330619.838, "dur": 0.259, + "args": { + "External id": 227044,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330624.227, "dur": 1.197, + "args": { + "External id": 227045,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330626.638, "dur": 0.174, + "args": { + "External id": 227046,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330628.233, "dur": 0.425, + "args": { + "External id": 227047,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330632.204, "dur": 0.288, + "args": { + "External id": 227048,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330633.898, "dur": 0.361, + "args": { + "External id": 227049,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115330635.559, "dur": 2.569, + "args": { + "External id": 227050,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115330691.937, "dur": 27.987, + "args": { + "External id": 227051,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115330784.314, "dur": 352.068, + "args": { + "External id": 227052,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 5851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115330812.082, "dur": 319.470, + "args": { + "External id": 227053,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5852, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115330822.880, "dur": 303.317, + "args": { + "External id": 227054,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 5853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115331155.992, "dur": 2.460, + "args": { + "External id": 227055,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5854, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 4183440, "tid": 4183440, + "ts": 667115331247.049, "dur": 7933.064, + "args": { + "External id": 227056,"Record function id": 0, "Ev Idx": 5855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115331342.078, "dur": 5.869, + "args": { + "External id": 227057,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 5856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115331351.187, "dur": 1.090, + "args": { + "External id": 227058,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115331354.204, "dur": 2.105, + "args": { + "External id": 227059,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115331357.981, "dur": 0.670, + "args": { + "External id": 227060,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115331360.396, "dur": 0.789, + "args": { + "External id": 227061,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115331362.857, "dur": 0.885, + "args": { + "External id": 227062,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115331365.756, "dur": 0.553, + "args": { + "External id": 227063,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115331367.955, "dur": 2.524, + "args": { + "External id": 227064,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115331372.103, "dur": 0.517, + "args": { + "External id": 227065,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115331374.263, "dur": 1.345, + "args": { + "External id": 227066,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115331394.353, "dur": 7746.009, + "args": { + "External id": 227067,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115331410.454, "dur": 7722.596, + "args": { + "External id": 227068,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115331432.376, "dur": 14.336, + "args": { + "External id": 227069,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115331449.612, "dur": 7646.355, + "args": { + "External id": 227070,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 5869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115331452.225, "dur": 7643.232, + "args": { + "External id": 227071,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 5870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115331458.957, "dur": 7.800, + "args": { + "External id": 227072,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115331469.005, "dur": 7622.946, + "args": { + "External id": 227073,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 5872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115339310.389, "dur": 41.178, + "args": { + "External id": 227074,"Sequence number": 2757771, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 5873 + } + }, + { + "ph": "s", "id": 185, "pid": 4183440, "tid": 4183440, "ts": 667115339310.389, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115339337.947, "dur": 8.481, + "args": { + "External id": 227075,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 5874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115339341.428, "dur": 4.826, + "args": { + "External id": 227076,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 5875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115339415.548, "dur": 98.648, + "args": { + "External id": 227077,"Record function id": 0, "Ev Idx": 5876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115339517.145, "dur": 1054.162, + "args": { + "External id": 227078,"Record function id": 0, "Ev Idx": 5877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115339559.946, "dur": 996.805, + "args": { + "External id": 227079,"Sequence number": 2757772, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 5878 + } + }, + { + "ph": "s", "id": 184, "pid": 4183440, "tid": 4183440, "ts": 667115339559.946, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115339629.467, "dur": 73.485, + "args": { + "External id": 227080,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115339719.080, "dur": 95.434, + "args": { + "External id": 227081,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115339823.641, "dur": 34.755, + "args": { + "External id": 227082,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115339867.471, "dur": 29.312, + "args": { + "External id": 227083,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115339922.136, "dur": 25.891, + "args": { + "External id": 227084,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115339965.454, "dur": 15.476, + "args": { + "External id": 227085,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115340000.038, "dur": 130.330, + "args": { + "External id": 227086,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 5885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115340050.320, "dur": 13.143, + "args": { + "External id": 227087,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 5886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115340055.971, "dur": 6.376, + "args": { + "External id": 227088,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115340066.454, "dur": 5.941, + "args": { + "External id": 227089,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115340073.848, "dur": 1.518, + "args": { + "External id": 227090,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115340078.071, "dur": 2.640, + "args": { + "External id": 227091,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115340142.263, "dur": 41.682, + "args": { + "External id": 227092,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115340213.590, "dur": 28.422, + "args": { + "External id": 227093,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115340250.398, "dur": 37.255, + "args": { + "External id": 227094,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115340296.484, "dur": 30.641, + "args": { + "External id": 227095,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115340348.233, "dur": 24.768, + "args": { + "External id": 227096,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 5895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115340378.706, "dur": 50.517, + "args": { + "External id": 227097,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 5896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115340448.240, "dur": 18.068, + "args": { + "External id": 227098,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 5897 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.13)", "pid": 4183440, "tid": 4183440, + "ts": 667115340637.814, "dur": 115.573, + "args": { + "External id": 227099,"Record function id": 0, "Ev Idx": 5898 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115340831.864, "dur": 47.701, + "args": { + "External id": 227100,"Record function id": 0, "Ev Idx": 5899 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.14)", "pid": 4183440, "tid": 4183440, + "ts": 667115340888.620, "dur": 9213.029, + "args": { + "External id": 227101,"Record function id": 0, "Ev Idx": 5900 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 4183440, "tid": 4183440, + "ts": 667115340898.146, "dur": 907.341, + "args": { + "External id": 227102,"Record function id": 0, "Ev Idx": 5901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115340977.336, "dur": 9.495, + "args": { + "External id": 227103,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115341000.731, "dur": 49.815, + "args": { + "External id": 227104,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341010.979, "dur": 2.497, + "args": { + "External id": 227105,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341018.127, "dur": 0.771, + "args": { + "External id": 227106,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341021.505, "dur": 0.771, + "args": { + "External id": 227107,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341024.009, "dur": 2.150, + "args": { + "External id": 227108,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341027.870, "dur": 0.493, + "args": { + "External id": 227109,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341032.835, "dur": 0.617, + "args": { + "External id": 227110,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341036.773, "dur": 0.849, + "args": { + "External id": 227111,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341038.921, "dur": 0.921, + "args": { + "External id": 227112,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341041.299, "dur": 2.628, + "args": { + "External id": 227113,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115341061.231, "dur": 46.775, + "args": { + "External id": 227114,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115341140.357, "dur": 111.351, + "args": { + "External id": 227115,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 5914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115341150.254, "dur": 4.994, + "args": { + "External id": 227116,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115341160.647, "dur": 10.967, + "args": { + "External id": 227117,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115341165.012, "dur": 6.177, + "args": { + "External id": 227118,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 5917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341169.088, "dur": 0.746, + "args": { + "External id": 227119,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115341178.739, "dur": 30.465, + "args": { + "External id": 227120,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341181.205, "dur": 0.641, + "args": { + "External id": 227121,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341183.774, "dur": 0.660, + "args": { + "External id": 227122,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341186.070, "dur": 2.519, + "args": { + "External id": 227123,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341190.284, "dur": 0.379, + "args": { + "External id": 227124,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341191.863, "dur": 0.746, + "args": { + "External id": 227125,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341195.790, "dur": 0.589, + "args": { + "External id": 227126,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341197.915, "dur": 0.800, + "args": { + "External id": 227127,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341199.784, "dur": 0.707, + "args": { + "External id": 227128,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115341203.562, "dur": 0.543, + "args": { + "External id": 227129,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115341219.752, "dur": 24.075, + "args": { + "External id": 227130,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115341302.506, "dur": 405.177, + "args": { + "External id": 227131,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 5930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115341325.383, "dur": 376.761, + "args": { + "External id": 227132,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5931, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115341335.776, "dur": 360.469, + "args": { + "External id": 227133,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 5932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115341731.112, "dur": 2.864, + "args": { + "External id": 227134,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5933, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 4183440, "tid": 4183440, + "ts": 667115341827.535, "dur": 8086.266, + "args": { + "External id": 227135,"Record function id": 0, "Ev Idx": 5934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115341926.567, "dur": 6.355, + "args": { + "External id": 227136,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 5935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115341936.527, "dur": 1.235, + "args": { + "External id": 227137,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115341939.323, "dur": 0.912, + "args": { + "External id": 227138,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115341941.887, "dur": 0.993, + "args": { + "External id": 227139,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115341944.443, "dur": 1.381, + "args": { + "External id": 227140,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115341947.594, "dur": 1.347, + "args": { + "External id": 227141,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 5940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115341950.599, "dur": 1.301, + "args": { + "External id": 227142,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 5941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115341953.995, "dur": 2.717, + "args": { + "External id": 227143,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115341958.649, "dur": 0.782, + "args": { + "External id": 227144,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115341961.464, "dur": 0.862, + "args": { + "External id": 227145,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 5944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115341980.812, "dur": 7894.194, + "args": { + "External id": 227146,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115341997.755, "dur": 7870.307, + "args": { + "External id": 227147,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 5946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115342018.156, "dur": 14.446, + "args": { + "External id": 227148,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115342035.615, "dur": 7800.709, + "args": { + "External id": 227149,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 5948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115342038.010, "dur": 7797.791, + "args": { + "External id": 227150,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 5949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115342043.829, "dur": 6.828, + "args": { + "External id": 227151,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115342052.267, "dur": 7780.105, + "args": { + "External id": 227152,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 5951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115350042.837, "dur": 34.757, + "args": { + "External id": 227153,"Sequence number": 2757773, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 5952 + } + }, + { + "ph": "s", "id": 183, "pid": 4183440, "tid": 4183440, "ts": 667115350042.837, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115350064.841, "dur": 7.843, + "args": { + "External id": 227154,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 5953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115350068.098, "dur": 4.367, + "args": { + "External id": 227155,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 5954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115350140.894, "dur": 90.123, + "args": { + "External id": 227156,"Record function id": 0, "Ev Idx": 5955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115350232.270, "dur": 1094.113, + "args": { + "External id": 227157,"Record function id": 0, "Ev Idx": 5956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115350271.712, "dur": 1041.577, + "args": { + "External id": 227158,"Sequence number": 2757774, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 5957 + } + }, + { + "ph": "s", "id": 182, "pid": 4183440, "tid": 4183440, "ts": 667115350271.712, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115350336.760, "dur": 39.351, + "args": { + "External id": 227159,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115350389.686, "dur": 89.114, + "args": { + "External id": 227160,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115350487.852, "dur": 56.167, + "args": { + "External id": 227161,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115350557.501, "dur": 30.035, + "args": { + "External id": 227162,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115350612.543, "dur": 27.020, + "args": { + "External id": 227163,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115350692.298, "dur": 19.921, + "args": { + "External id": 227164,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115350731.498, "dur": 137.824, + "args": { + "External id": 227165,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 5964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115350789.549, "dur": 12.984, + "args": { + "External id": 227166,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 5965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115350794.361, "dur": 7.444, + "args": { + "External id": 227167,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115350805.019, "dur": 5.684, + "args": { + "External id": 227168,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115350812.206, "dur": 1.642, + "args": { + "External id": 227169,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115350816.300, "dur": 2.649, + "args": { + "External id": 227170,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115350880.813, "dur": 54.962, + "args": { + "External id": 227171,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 5970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115350971.041, "dur": 29.373, + "args": { + "External id": 227172,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 5971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115351009.025, "dur": 37.908, + "args": { + "External id": 227173,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115351055.309, "dur": 50.649, + "args": { + "External id": 227174,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 5973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115351127.762, "dur": 26.315, + "args": { + "External id": 227175,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 5974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115351159.924, "dur": 43.746, + "args": { + "External id": 227176,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 5975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115351223.550, "dur": 19.872, + "args": { + "External id": 227177,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 5976 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.14)", "pid": 4183440, "tid": 4183440, + "ts": 667115351390.443, "dur": 77.449, + "args": { + "External id": 227178,"Record function id": 0, "Ev Idx": 5977 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115351563.844, "dur": 48.531, + "args": { + "External id": 227179,"Record function id": 0, "Ev Idx": 5978 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.15)", "pid": 4183440, "tid": 4183440, + "ts": 667115351621.490, "dur": 9450.154, + "args": { + "External id": 227180,"Record function id": 0, "Ev Idx": 5979 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 4183440, "tid": 4183440, + "ts": 667115351629.459, "dur": 905.429, + "args": { + "External id": 227181,"Record function id": 0, "Ev Idx": 5980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115351749.605, "dur": 10.174, + "args": { + "External id": 227182,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115351773.628, "dur": 39.357, + "args": { + "External id": 227183,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351779.685, "dur": 2.715, + "args": { + "External id": 227184,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351786.739, "dur": 0.562, + "args": { + "External id": 227185,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351788.715, "dur": 0.717, + "args": { + "External id": 227186,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351790.794, "dur": 0.378, + "args": { + "External id": 227187,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351794.424, "dur": 0.763, + "args": { + "External id": 227188,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351796.384, "dur": 0.640, + "args": { + "External id": 227189,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351798.531, "dur": 2.477, + "args": { + "External id": 227190,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351802.724, "dur": 0.880, + "args": { + "External id": 227191,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351804.940, "dur": 0.997, + "args": { + "External id": 227192,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115351824.088, "dur": 43.252, + "args": { + "External id": 227193,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 5992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115351900.498, "dur": 117.943, + "args": { + "External id": 227194,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 5993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115351911.037, "dur": 4.521, + "args": { + "External id": 227195,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115351920.553, "dur": 10.304, + "args": { + "External id": 227196,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115351925.095, "dur": 5.330, + "args": { + "External id": 227197,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 5996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351928.416, "dur": 0.866, + "args": { + "External id": 227198,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 5997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115351937.330, "dur": 30.387, + "args": { + "External id": 227199,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 5998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351939.395, "dur": 2.708, + "args": { + "External id": 227200,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 5999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351943.259, "dur": 0.645, + "args": { + "External id": 227201,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351945.029, "dur": 0.723, + "args": { + "External id": 227202,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351949.510, "dur": 0.506, + "args": { + "External id": 227203,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351951.204, "dur": 0.605, + "args": { + "External id": 227204,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351953.037, "dur": 0.485, + "args": { + "External id": 227205,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351957.233, "dur": 0.690, + "args": { + "External id": 227206,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351959.286, "dur": 0.373, + "args": { + "External id": 227207,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115351961.042, "dur": 2.248, + "args": { + "External id": 227208,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115351987.829, "dur": 22.348, + "args": { + "External id": 227209,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 6008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115352072.579, "dur": 352.702, + "args": { + "External id": 227210,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 6009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115352099.744, "dur": 320.775, + "args": { + "External id": 227211,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6010, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115352112.532, "dur": 302.351, + "args": { + "External id": 227212,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 6011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115352444.133, "dur": 2.437, + "args": { + "External id": 227213,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6012, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 4183440, "tid": 4183440, + "ts": 667115352557.682, "dur": 8324.918, + "args": { + "External id": 227214,"Record function id": 0, "Ev Idx": 6013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115352689.015, "dur": 7.243, + "args": { + "External id": 227215,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 6014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115352700.982, "dur": 1.647, + "args": { + "External id": 227216,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 6015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115352704.475, "dur": 1.387, + "args": { + "External id": 227217,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115352707.539, "dur": 1.474, + "args": { + "External id": 227218,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115352710.895, "dur": 0.860, + "args": { + "External id": 227219,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115352713.950, "dur": 1.194, + "args": { + "External id": 227220,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115352717.399, "dur": 1.229, + "args": { + "External id": 227221,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 6020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115352720.344, "dur": 1.878, + "args": { + "External id": 227222,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 6021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115352724.319, "dur": 1.050, + "args": { + "External id": 227223,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 6022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115352727.087, "dur": 1.246, + "args": { + "External id": 227224,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 6023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115352748.373, "dur": 8095.210, + "args": { + "External id": 227225,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 6024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115352764.766, "dur": 8072.215, + "args": { + "External id": 227226,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 6025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115352781.148, "dur": 15.296, + "args": { + "External id": 227227,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115352799.275, "dur": 8004.530, + "args": { + "External id": 227228,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 6027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115352802.158, "dur": 8001.201, + "args": { + "External id": 227229,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 6028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115352807.999, "dur": 7.144, + "args": { + "External id": 227230,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115352817.021, "dur": 7982.756, + "args": { + "External id": 227231,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 6030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115361015.452, "dur": 31.441, + "args": { + "External id": 227232,"Sequence number": 2757775, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 6031 + } + }, + { + "ph": "s", "id": 181, "pid": 4183440, "tid": 4183440, "ts": 667115361015.452, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115361034.200, "dur": 7.850, + "args": { + "External id": 227233,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 6032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115361037.464, "dur": 4.370, + "args": { + "External id": 227234,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115361110.234, "dur": 91.646, + "args": { + "External id": 227235,"Record function id": 0, "Ev Idx": 6034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115361203.750, "dur": 1109.148, + "args": { + "External id": 227236,"Record function id": 0, "Ev Idx": 6035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115361245.927, "dur": 1053.908, + "args": { + "External id": 227237,"Sequence number": 2757776, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 6036 + } + }, + { + "ph": "s", "id": 180, "pid": 4183440, "tid": 4183440, "ts": 667115361245.927, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115361316.290, "dur": 42.132, + "args": { + "External id": 227238,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115361371.230, "dur": 93.730, + "args": { + "External id": 227239,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115361473.829, "dur": 54.045, + "args": { + "External id": 227240,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115361539.544, "dur": 32.167, + "args": { + "External id": 227241,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115361598.936, "dur": 25.887, + "args": { + "External id": 227242,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115361642.060, "dur": 50.450, + "args": { + "External id": 227243,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115361713.699, "dur": 134.835, + "args": { + "External id": 227244,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115361765.823, "dur": 13.295, + "args": { + "External id": 227245,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 6044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115361771.163, "dur": 7.117, + "args": { + "External id": 227246,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115361781.804, "dur": 5.745, + "args": { + "External id": 227247,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115361788.962, "dur": 1.691, + "args": { + "External id": 227248,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115361792.747, "dur": 2.986, + "args": { + "External id": 227249,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115361860.120, "dur": 52.222, + "args": { + "External id": 227250,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115361945.403, "dur": 30.265, + "args": { + "External id": 227251,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115361983.757, "dur": 39.057, + "args": { + "External id": 227252,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 6051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115362030.993, "dur": 48.387, + "args": { + "External id": 227253,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 6052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115362101.629, "dur": 29.027, + "args": { + "External id": 227254,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 6053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115362136.069, "dur": 48.696, + "args": { + "External id": 227255,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 6054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115362205.044, "dur": 19.736, + "args": { + "External id": 227256,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 6055 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.15)", "pid": 4183440, "tid": 4183440, + "ts": 667115362377.144, "dur": 78.992, + "args": { + "External id": 227257,"Record function id": 0, "Ev Idx": 6056 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115362550.106, "dur": 49.022, + "args": { + "External id": 227258,"Record function id": 0, "Ev Idx": 6057 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.16)", "pid": 4183440, "tid": 4183440, + "ts": 667115362608.491, "dur": 9290.037, + "args": { + "External id": 227259,"Record function id": 0, "Ev Idx": 6058 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 4183440, "tid": 4183440, + "ts": 667115362617.469, "dur": 961.041, + "args": { + "External id": 227260,"Record function id": 0, "Ev Idx": 6059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115362739.772, "dur": 10.812, + "args": { + "External id": 227261,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115362764.397, "dur": 37.158, + "args": { + "External id": 227262,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 6061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362770.165, "dur": 2.393, + "args": { + "External id": 227263,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362778.077, "dur": 0.615, + "args": { + "External id": 227264,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362779.810, "dur": 0.686, + "args": { + "External id": 227265,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362782.695, "dur": 0.539, + "args": { + "External id": 227266,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362786.181, "dur": 0.720, + "args": { + "External id": 227267,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362788.411, "dur": 0.502, + "args": { + "External id": 227268,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362789.794, "dur": 2.215, + "args": { + "External id": 227269,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362793.350, "dur": 0.442, + "args": { + "External id": 227270,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362794.576, "dur": 0.406, + "args": { + "External id": 227271,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115362816.398, "dur": 42.788, + "args": { + "External id": 227272,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 6071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115362893.951, "dur": 109.148, + "args": { + "External id": 227273,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 6072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115362904.296, "dur": 6.001, + "args": { + "External id": 227274,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115362915.407, "dur": 10.406, + "args": { + "External id": 227275,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 6074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115362919.930, "dur": 5.436, + "args": { + "External id": 227276,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 6075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362923.099, "dur": 1.001, + "args": { + "External id": 227277,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 6076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115362932.053, "dur": 29.803, + "args": { + "External id": 227278,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 6077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362934.009, "dur": 0.842, + "args": { + "External id": 227279,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362936.692, "dur": 2.848, + "args": { + "External id": 227280,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362940.451, "dur": 0.502, + "args": { + "External id": 227281,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362942.669, "dur": 0.978, + "args": { + "External id": 227282,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362946.990, "dur": 0.482, + "args": { + "External id": 227283,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362949.023, "dur": 0.694, + "args": { + "External id": 227284,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362950.636, "dur": 0.724, + "args": { + "External id": 227285,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362954.744, "dur": 0.827, + "args": { + "External id": 227286,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115362956.500, "dur": 0.635, + "args": { + "External id": 227287,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115362972.342, "dur": 22.438, + "args": { + "External id": 227288,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 6087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115363055.313, "dur": 405.105, + "args": { + "External id": 227289,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 6088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115363082.275, "dur": 372.782, + "args": { + "External id": 227290,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6089, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115363093.140, "dur": 353.874, + "args": { + "External id": 227291,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 6090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115363479.886, "dur": 2.434, + "args": { + "External id": 227292,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6091, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 4183440, "tid": 4183440, + "ts": 667115363601.244, "dur": 8099.906, + "args": { + "External id": 227293,"Record function id": 0, "Ev Idx": 6092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115363738.477, "dur": 7.305, + "args": { + "External id": 227294,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 6093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115363749.371, "dur": 1.127, + "args": { + "External id": 227295,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 6094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115363752.095, "dur": 1.149, + "args": { + "External id": 227296,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115363754.659, "dur": 0.880, + "args": { + "External id": 227297,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115363756.971, "dur": 1.204, + "args": { + "External id": 227298,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115363759.559, "dur": 0.786, + "args": { + "External id": 227299,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115363762.123, "dur": 1.256, + "args": { + "External id": 227300,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 6099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115363765.589, "dur": 2.473, + "args": { + "External id": 227301,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 6100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115363769.757, "dur": 0.969, + "args": { + "External id": 227302,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 6101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115363772.455, "dur": 1.200, + "args": { + "External id": 227303,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 6102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115363792.658, "dur": 7844.997, + "args": { + "External id": 227304,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 6103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115363808.783, "dur": 7821.875, + "args": { + "External id": 227305,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 6104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115363824.189, "dur": 15.311, + "args": { + "External id": 227306,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115363842.479, "dur": 7754.785, + "args": { + "External id": 227307,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 6106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115363845.254, "dur": 7751.594, + "args": { + "External id": 227308,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 6107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115363851.366, "dur": 7.107, + "args": { + "External id": 227309,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115363860.246, "dur": 7733.471, + "args": { + "External id": 227310,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 6109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115371842.761, "dur": 29.912, + "args": { + "External id": 227311,"Sequence number": 2757777, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 6110 + } + }, + { + "ph": "s", "id": 179, "pid": 4183440, "tid": 4183440, "ts": 667115371842.761, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115371859.253, "dur": 8.246, + "args": { + "External id": 227312,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 6111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115371862.512, "dur": 4.707, + "args": { + "External id": 227313,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115371939.638, "dur": 89.638, + "args": { + "External id": 227314,"Record function id": 0, "Ev Idx": 6113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115372031.055, "dur": 1150.077, + "args": { + "External id": 227315,"Record function id": 0, "Ev Idx": 6114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115372069.807, "dur": 1097.272, + "args": { + "External id": 227316,"Sequence number": 2757778, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 6115 + } + }, + { + "ph": "s", "id": 178, "pid": 4183440, "tid": 4183440, "ts": 667115372069.807, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115372137.429, "dur": 42.913, + "args": { + "External id": 227317,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115372192.987, "dur": 94.198, + "args": { + "External id": 227318,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115372295.896, "dur": 34.572, + "args": { + "External id": 227319,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115372339.281, "dur": 29.109, + "args": { + "External id": 227320,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115372397.332, "dur": 29.494, + "args": { + "External id": 227321,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115372442.871, "dur": 15.634, + "args": { + "External id": 227322,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115372474.209, "dur": 157.584, + "args": { + "External id": 227323,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115372545.380, "dur": 12.827, + "args": { + "External id": 227324,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 6123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115372550.168, "dur": 6.871, + "args": { + "External id": 227325,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115372561.000, "dur": 5.639, + "args": { + "External id": 227326,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115372567.967, "dur": 1.769, + "args": { + "External id": 227327,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115372572.197, "dur": 5.302, + "args": { + "External id": 227328,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115372709.649, "dur": 63.212, + "args": { + "External id": 227329,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115372813.544, "dur": 28.781, + "args": { + "External id": 227330,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115372851.650, "dur": 53.818, + "args": { + "External id": 227331,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 6130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115372914.584, "dur": 53.895, + "args": { + "External id": 227332,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 6131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115372990.831, "dur": 25.359, + "args": { + "External id": 227333,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 6132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115373022.290, "dur": 33.305, + "args": { + "External id": 227334,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 6133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115373075.979, "dur": 18.334, + "args": { + "External id": 227335,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 6134 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.16)", "pid": 4183440, "tid": 4183440, + "ts": 667115373249.366, "dur": 75.343, + "args": { + "External id": 227336,"Record function id": 0, "Ev Idx": 6135 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115373395.402, "dur": 47.131, + "args": { + "External id": 227337,"Record function id": 0, "Ev Idx": 6136 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.17)", "pid": 4183440, "tid": 4183440, + "ts": 667115373450.742, "dur": 9522.811, + "args": { + "External id": 227338,"Record function id": 0, "Ev Idx": 6137 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 4183440, "tid": 4183440, + "ts": 667115373458.507, "dur": 899.028, + "args": { + "External id": 227339,"Record function id": 0, "Ev Idx": 6138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115373553.797, "dur": 9.728, + "args": { + "External id": 227340,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115373577.969, "dur": 37.745, + "args": { + "External id": 227341,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 6140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373583.670, "dur": 2.353, + "args": { + "External id": 227342,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373591.069, "dur": 0.649, + "args": { + "External id": 227343,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373593.386, "dur": 0.609, + "args": { + "External id": 227344,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373595.596, "dur": 0.715, + "args": { + "External id": 227345,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373599.836, "dur": 0.576, + "args": { + "External id": 227346,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373601.576, "dur": 0.607, + "args": { + "External id": 227347,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373603.016, "dur": 2.169, + "args": { + "External id": 227348,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373606.536, "dur": 0.487, + "args": { + "External id": 227349,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373608.025, "dur": 0.404, + "args": { + "External id": 227350,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115373627.736, "dur": 79.209, + "args": { + "External id": 227351,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 6150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115373743.897, "dur": 119.378, + "args": { + "External id": 227352,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 6151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115373754.839, "dur": 6.145, + "args": { + "External id": 227353,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115373766.346, "dur": 11.299, + "args": { + "External id": 227354,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 6153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115373770.859, "dur": 6.349, + "args": { + "External id": 227355,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 6154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373774.670, "dur": 1.072, + "args": { + "External id": 227356,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 6155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115373784.789, "dur": 31.305, + "args": { + "External id": 227357,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 6156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373786.578, "dur": 2.499, + "args": { + "External id": 227358,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373790.348, "dur": 0.859, + "args": { + "External id": 227359,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373792.397, "dur": 0.457, + "args": { + "External id": 227360,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373796.434, "dur": 0.935, + "args": { + "External id": 227361,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373798.547, "dur": 0.855, + "args": { + "External id": 227362,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373800.999, "dur": 0.624, + "args": { + "External id": 227363,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373804.849, "dur": 0.571, + "args": { + "External id": 227364,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373807.164, "dur": 0.481, + "args": { + "External id": 227365,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115373808.814, "dur": 2.673, + "args": { + "External id": 227366,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115373829.858, "dur": 24.479, + "args": { + "External id": 227367,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 6166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115373917.432, "dur": 353.202, + "args": { + "External id": 227368,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 6167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115373943.891, "dur": 321.534, + "args": { + "External id": 227369,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6168, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115373954.577, "dur": 305.679, + "args": { + "External id": 227370,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 6169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115374288.904, "dur": 2.218, + "args": { + "External id": 227371,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6170, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 4183440, "tid": 4183440, + "ts": 667115374378.168, "dur": 8403.130, + "args": { + "External id": 227372,"Record function id": 0, "Ev Idx": 6171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115374470.575, "dur": 5.862, + "args": { + "External id": 227373,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 6172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115374479.513, "dur": 1.241, + "args": { + "External id": 227374,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 6173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115374482.249, "dur": 1.001, + "args": { + "External id": 227375,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115374485.103, "dur": 0.812, + "args": { + "External id": 227376,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115374487.579, "dur": 0.816, + "args": { + "External id": 227377,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115374490.228, "dur": 21.255, + "args": { + "External id": 227378,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115374516.116, "dur": 1.027, + "args": { + "External id": 227379,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 6178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115374519.467, "dur": 2.570, + "args": { + "External id": 227380,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 6179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115374523.959, "dur": 1.052, + "args": { + "External id": 227381,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 6180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115374526.893, "dur": 1.021, + "args": { + "External id": 227382,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 6181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115374547.060, "dur": 8194.275, + "args": { + "External id": 227383,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 6182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115374562.885, "dur": 8171.899, + "args": { + "External id": 227384,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 6183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115374579.924, "dur": 14.174, + "args": { + "External id": 227385,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115374596.814, "dur": 8106.065, + "args": { + "External id": 227386,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 6185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115374599.618, "dur": 8102.745, + "args": { + "External id": 227387,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 6186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115374606.008, "dur": 7.740, + "args": { + "External id": 227388,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115374615.501, "dur": 8083.501, + "args": { + "External id": 227389,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 6188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115382919.834, "dur": 29.098, + "args": { + "External id": 227390,"Sequence number": 2757779, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 6189 + } + }, + { + "ph": "s", "id": 177, "pid": 4183440, "tid": 4183440, "ts": 667115382919.834, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115382935.792, "dur": 8.070, + "args": { + "External id": 227391,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 6190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115382938.964, "dur": 4.580, + "args": { + "External id": 227392,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115383013.784, "dur": 87.103, + "args": { + "External id": 227393,"Record function id": 0, "Ev Idx": 6192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115383102.656, "dur": 1092.231, + "args": { + "External id": 227394,"Record function id": 0, "Ev Idx": 6193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115383143.164, "dur": 1036.876, + "args": { + "External id": 227395,"Sequence number": 2757780, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 6194 + } + }, + { + "ph": "s", "id": 176, "pid": 4183440, "tid": 4183440, "ts": 667115383143.164, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115383209.849, "dur": 39.932, + "args": { + "External id": 227396,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115383262.660, "dur": 89.339, + "args": { + "External id": 227397,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115383360.614, "dur": 33.803, + "args": { + "External id": 227398,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115383403.161, "dur": 29.440, + "args": { + "External id": 227399,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115383456.689, "dur": 24.936, + "args": { + "External id": 227400,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115383517.881, "dur": 17.075, + "args": { + "External id": 227401,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115383553.323, "dur": 167.892, + "args": { + "External id": 227402,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115383604.435, "dur": 12.832, + "args": { + "External id": 227403,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 6202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115383609.761, "dur": 6.722, + "args": { + "External id": 227404,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115383619.992, "dur": 6.341, + "args": { + "External id": 227405,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115383627.931, "dur": 1.657, + "args": { + "External id": 227406,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115383632.046, "dur": 2.996, + "args": { + "External id": 227407,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115383735.013, "dur": 53.223, + "args": { + "External id": 227408,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115383821.664, "dur": 26.856, + "args": { + "External id": 227409,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115383856.767, "dur": 38.860, + "args": { + "External id": 227410,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 6209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115383905.148, "dur": 50.719, + "args": { + "External id": 227411,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 6210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115383979.039, "dur": 27.770, + "args": { + "External id": 227412,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 6211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115384013.728, "dur": 53.064, + "args": { + "External id": 227413,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 6212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115384086.994, "dur": 18.840, + "args": { + "External id": 227414,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 6213 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.17)", "pid": 4183440, "tid": 4183440, + "ts": 667115384259.546, "dur": 74.708, + "args": { + "External id": 227415,"Record function id": 0, "Ev Idx": 6214 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115384405.508, "dur": 47.339, + "args": { + "External id": 227416,"Record function id": 0, "Ev Idx": 6215 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.18)", "pid": 4183440, "tid": 4183440, + "ts": 667115384461.287, "dur": 9347.611, + "args": { + "External id": 227417,"Record function id": 0, "Ev Idx": 6216 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 4183440, "tid": 4183440, + "ts": 667115384468.707, "dur": 906.329, + "args": { + "External id": 227418,"Record function id": 0, "Ev Idx": 6217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115384571.310, "dur": 10.351, + "args": { + "External id": 227419,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115384595.983, "dur": 36.931, + "args": { + "External id": 227420,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 6219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384601.310, "dur": 2.277, + "args": { + "External id": 227421,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384608.733, "dur": 0.708, + "args": { + "External id": 227422,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384610.621, "dur": 0.443, + "args": { + "External id": 227423,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384612.319, "dur": 0.893, + "args": { + "External id": 227424,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384616.327, "dur": 0.602, + "args": { + "External id": 227425,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384618.282, "dur": 0.897, + "args": { + "External id": 227426,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384620.235, "dur": 2.492, + "args": { + "External id": 227427,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384624.231, "dur": 0.362, + "args": { + "External id": 227428,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384625.899, "dur": 0.367, + "args": { + "External id": 227429,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115384644.412, "dur": 76.162, + "args": { + "External id": 227430,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 6229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115384757.627, "dur": 117.698, + "args": { + "External id": 227431,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 6230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115384773.100, "dur": 7.419, + "args": { + "External id": 227432,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115384785.679, "dur": 11.706, + "args": { + "External id": 227433,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 6232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115384790.219, "dur": 6.730, + "args": { + "External id": 227434,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 6233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384794.008, "dur": 1.019, + "args": { + "External id": 227435,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 6234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115384804.259, "dur": 28.409, + "args": { + "External id": 227436,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 6235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384806.311, "dur": 0.678, + "args": { + "External id": 227437,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384808.157, "dur": 2.466, + "args": { + "External id": 227438,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384811.841, "dur": 0.452, + "args": { + "External id": 227439,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384813.414, "dur": 0.690, + "args": { + "External id": 227440,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384817.985, "dur": 0.439, + "args": { + "External id": 227441,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384819.528, "dur": 0.744, + "args": { + "External id": 227442,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384821.315, "dur": 0.417, + "args": { + "External id": 227443,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384824.952, "dur": 0.544, + "args": { + "External id": 227444,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115384826.951, "dur": 0.432, + "args": { + "External id": 227445,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115384844.492, "dur": 22.556, + "args": { + "External id": 227446,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 6245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115384929.366, "dur": 358.043, + "args": { + "External id": 227447,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 6246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115384956.475, "dur": 326.383, + "args": { + "External id": 227448,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6247, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115384967.394, "dur": 309.479, + "args": { + "External id": 227449,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 6248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115385306.643, "dur": 2.325, + "args": { + "External id": 227450,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6249, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 4183440, "tid": 4183440, + "ts": 667115385394.724, "dur": 8193.688, + "args": { + "External id": 227451,"Record function id": 0, "Ev Idx": 6250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115385485.861, "dur": 25.954, + "args": { + "External id": 227452,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 6251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115385517.413, "dur": 1.472, + "args": { + "External id": 227453,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 6252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115385520.640, "dur": 1.267, + "args": { + "External id": 227454,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115385523.679, "dur": 0.853, + "args": { + "External id": 227455,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115385526.052, "dur": 1.066, + "args": { + "External id": 227456,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115385528.935, "dur": 1.356, + "args": { + "External id": 227457,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115385532.246, "dur": 1.062, + "args": { + "External id": 227458,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 6257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115385535.099, "dur": 2.277, + "args": { + "External id": 227459,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 6258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115385539.652, "dur": 0.871, + "args": { + "External id": 227460,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 6259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115385542.419, "dur": 0.918, + "args": { + "External id": 227461,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 6260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115385562.588, "dur": 7987.646, + "args": { + "External id": 227462,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 6261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115385578.731, "dur": 7965.170, + "args": { + "External id": 227463,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 6262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115385594.043, "dur": 14.303, + "args": { + "External id": 227464,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115385611.396, "dur": 7899.933, + "args": { + "External id": 227465,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 6264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115385613.664, "dur": 7896.990, + "args": { + "External id": 227466,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 6265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115385620.034, "dur": 5.678, + "args": { + "External id": 227467,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115385627.429, "dur": 7880.117, + "args": { + "External id": 227468,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 6267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115393753.038, "dur": 30.198, + "args": { + "External id": 227469,"Sequence number": 2757781, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 6268 + } + }, + { + "ph": "s", "id": 175, "pid": 4183440, "tid": 4183440, "ts": 667115393753.038, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115393769.677, "dur": 8.343, + "args": { + "External id": 227470,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 6269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115393773.017, "dur": 4.687, + "args": { + "External id": 227471,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115393848.174, "dur": 89.900, + "args": { + "External id": 227472,"Record function id": 0, "Ev Idx": 6271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115393939.473, "dur": 1070.078, + "args": { + "External id": 227473,"Record function id": 0, "Ev Idx": 6272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115393980.670, "dur": 1015.017, + "args": { + "External id": 227474,"Sequence number": 2757782, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 6273 + } + }, + { + "ph": "s", "id": 174, "pid": 4183440, "tid": 4183440, "ts": 667115393980.670, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115394051.209, "dur": 42.530, + "args": { + "External id": 227475,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115394108.896, "dur": 91.950, + "args": { + "External id": 227476,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115394209.624, "dur": 34.611, + "args": { + "External id": 227477,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115394250.053, "dur": 29.621, + "args": { + "External id": 227478,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115394304.655, "dur": 24.103, + "args": { + "External id": 227479,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115394343.509, "dur": 15.395, + "args": { + "External id": 227480,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115394373.357, "dur": 146.169, + "args": { + "External id": 227481,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115394423.251, "dur": 10.939, + "args": { + "External id": 227482,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 6281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115394427.877, "dur": 5.530, + "args": { + "External id": 227483,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115394436.863, "dur": 4.603, + "args": { + "External id": 227484,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115394442.777, "dur": 3.570, + "args": { + "External id": 227485,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115394448.633, "dur": 2.576, + "args": { + "External id": 227486,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115394532.722, "dur": 47.654, + "args": { + "External id": 227487,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115394613.811, "dur": 28.720, + "args": { + "External id": 227488,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115394686.681, "dur": 44.094, + "args": { + "External id": 227489,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 6288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115394740.772, "dur": 32.992, + "args": { + "External id": 227490,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 6289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115394799.907, "dur": 27.968, + "args": { + "External id": 227491,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 6290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115394834.341, "dur": 54.108, + "args": { + "External id": 227492,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 6291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115394905.851, "dur": 19.927, + "args": { + "External id": 227493,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 6292 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.18)", "pid": 4183440, "tid": 4183440, + "ts": 667115395076.464, "dur": 78.562, + "args": { + "External id": 227494,"Record function id": 0, "Ev Idx": 6293 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 4183440, "tid": 4183440, + "ts": 667115395226.465, "dur": 48.297, + "args": { + "External id": 227495,"Record function id": 0, "Ev Idx": 6294 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.19)", "pid": 4183440, "tid": 4183440, + "ts": 667115395283.668, "dur": 9302.648, + "args": { + "External id": 227496,"Record function id": 0, "Ev Idx": 6295 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 4183440, "tid": 4183440, + "ts": 667115395291.568, "dur": 911.353, + "args": { + "External id": 227497,"Record function id": 0, "Ev Idx": 6296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115395372.976, "dur": 8.541, + "args": { + "External id": 227498,"Record function id": 0, "Concrete Inputs": ["[1605888]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115395394.748, "dur": 37.863, + "args": { + "External id": 227499,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 6298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395400.171, "dur": 2.382, + "args": { + "External id": 227500,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395407.653, "dur": 0.318, + "args": { + "External id": 227501,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "128"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395409.052, "dur": 1.000, + "args": { + "External id": 227502,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "131200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395411.244, "dur": 0.771, + "args": { + "External id": 227503,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "262272"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395415.273, "dur": 0.907, + "args": { + "External id": 227504,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "393344"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395417.217, "dur": 0.745, + "args": { + "External id": 227505,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "524416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395418.984, "dur": 2.653, + "args": { + "External id": 227506,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395422.841, "dur": 0.580, + "args": { + "External id": 227507,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "884992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395424.581, "dur": 0.636, + "args": { + "External id": 227508,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "1245440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115395444.009, "dur": 38.439, + "args": { + "External id": 227509,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 6308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 4183440, "tid": 4183440, + "ts": 667115395538.853, "dur": 154.581, + "args": { + "External id": 227510,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1605888", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [], [], [], [], [], []], "Ev Idx": 6309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115395550.458, "dur": 6.603, + "args": { + "External id": 227511,"Record function id": 0, "Concrete Inputs": ["[12847104]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 4183440, "tid": 4183440, + "ts": 667115395562.354, "dur": 11.487, + "args": { + "External id": 227512,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "1605888"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 6311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115395566.968, "dur": 6.415, + "args": { + "External id": 227513,"Record function id": 0, "Concrete Inputs": ["", "0", "6423552", "8029440", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[12847104], [], [], [], []], "Ev Idx": 6312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395570.706, "dur": 1.036, + "args": { + "External id": 227514,"Record function id": 0, "Concrete Inputs": ["", "[1605888]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[12847104], [], [], []], "Ev Idx": 6313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 4183440, "tid": 4183440, + "ts": 667115395580.603, "dur": 30.373, + "args": { + "External id": 227515,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1605888], [], []], "Ev Idx": 6314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395582.194, "dur": 2.536, + "args": { + "External id": 227516,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6423552"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395586.019, "dur": 0.654, + "args": { + "External id": 227517,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6423680"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395587.602, "dur": 0.756, + "args": { + "External id": 227518,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6554752"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395591.986, "dur": 0.618, + "args": { + "External id": 227519,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6685824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395593.869, "dur": 0.763, + "args": { + "External id": 227520,"Record function id": 0, "Concrete Inputs": ["", "[131072]", "[1]", "6816896"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395596.310, "dur": 0.757, + "args": { + "External id": 227521,"Record function id": 0, "Concrete Inputs": ["", "[128]", "[1]", "6947968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395600.059, "dur": 0.701, + "args": { + "External id": 227522,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "6948096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395602.220, "dur": 0.781, + "args": { + "External id": 227523,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7308544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115395604.269, "dur": 2.423, + "args": { + "External id": 227524,"Record function id": 0, "Concrete Inputs": ["", "[360448]", "[1]", "7668992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1605888], [], [], []], "Ev Idx": 6323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115395625.074, "dur": 23.065, + "args": { + "External id": 227525,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], [[128], [131072], [131072], [131072], [131072], [128], [360448], [360448], [360448]], []], "Ev Idx": 6324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 4183440, "tid": 4183440, + "ts": 667115395754.099, "dur": 361.739, + "args": { + "External id": 227526,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[12847104], [1605888], [], [], []], "Ev Idx": 6325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115395781.286, "dur": 329.887, + "args": { + "External id": 227527,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 12847104, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1605888], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6326, "In msg nelems": 1605888 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 4183440, "tid": 4183440, + "ts": 667115395792.197, "dur": 313.298, + "args": { + "External id": 227528,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[1605888]], "Ev Idx": 6327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115396133.897, "dur": 2.332, + "args": { + "External id": 227529,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6328, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 4183440, "tid": 4183440, + "ts": 667115396223.610, "dur": 8147.544, + "args": { + "External id": 227530,"Record function id": 0, "Ev Idx": 6329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115396325.060, "dur": 6.110, + "args": { + "External id": 227531,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[12847104], []], "Ev Idx": 6330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115396343.856, "dur": 1.582, + "args": { + "External id": 227532,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 6331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115396347.312, "dur": 1.109, + "args": { + "External id": 227533,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115396350.231, "dur": 1.334, + "args": { + "External id": 227534,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115396353.114, "dur": 1.137, + "args": { + "External id": 227535,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115396355.459, "dur": 0.862, + "args": { + "External id": 227536,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1048576], []], "Ev Idx": 6335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115396358.107, "dur": 1.437, + "args": { + "External id": 227537,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1024], []], "Ev Idx": 6336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115396361.515, "dur": 2.139, + "args": { + "External id": 227538,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 6337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115396365.524, "dur": 0.958, + "args": { + "External id": 227539,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 6338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115396368.319, "dur": 0.771, + "args": { + "External id": 227540,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2883584], []], "Ev Idx": 6339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115396390.049, "dur": 7941.570, + "args": { + "External id": 227541,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 6340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115396406.109, "dur": 7918.745, + "args": { + "External id": 227542,"Record function id": 0, "Concrete Inputs": ["", "[128, 131072, 131072, 131072, 131072, 128, 360448, 360448, 360448]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[1605888, 1], [], [], [[128, 1], [131072, 1], [131072, 1], [131072, 1], [131072, 1], [128, 1], [360448, 1], [360448, 1], [360448, 1]]], "Input Dims": [[8, 1605888], [], [], [[8, 128], [8, 131072], [8, 131072], [8, 131072], [8, 131072], [8, 128], [8, 360448], [8, 360448], [8, 360448]]], "Ev Idx": 6341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115396419.895, "dur": 14.186, + "args": { + "External id": 227543,"Record function id": 0, "Concrete Inputs": ["[823]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115396436.885, "dur": 7856.585, + "args": { + "External id": 227544,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], [], []], "Ev Idx": 6343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115396439.183, "dur": 7853.695, + "args": { + "External id": 227545,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[823], [], [], [], [], [], []], "Ev Idx": 6344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115396445.332, "dur": 5.971, + "args": { + "External id": 227546,"Record function id": 0, "Concrete Inputs": ["[823]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115396453.007, "dur": 7836.466, + "args": { + "External id": 227547,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[823], [823], []], "Ev Idx": 6346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115404527.835, "dur": 32.361, + "args": { + "External id": 227548,"Sequence number": 2757783, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024]], "Ev Idx": 6347 + } + }, + { + "ph": "s", "id": 173, "pid": 4183440, "tid": 4183440, "ts": 667115404527.835, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115404546.099, "dur": 8.961, + "args": { + "External id": 227549,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1]], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024]], "Ev Idx": 6348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115404549.617, "dur": 5.037, + "args": { + "External id": 227550,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115404627.267, "dur": 116.183, + "args": { + "External id": 227551,"Record function id": 0, "Ev Idx": 6350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 4183440, "tid": 4183440, + "ts": 667115404746.650, "dur": 1054.408, + "args": { + "External id": 227552,"Record function id": 0, "Ev Idx": 6351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115404789.599, "dur": 997.020, + "args": { + "External id": 227553,"Sequence number": 2757784, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1], [1024, 1], [1024, 1], [1024, 1], [32, 1], [32, 1], [1024, 1], [1], [1024, 1], [1024, 1], [2816, 1]], "Input Dims": [[16, 4096, 1024], [1024], [1024, 1024], [1024, 1024], [1024, 1024], [8192, 32], [8192, 32], [1024, 1024], [1024], [2816, 1024], [2816, 1024], [1024, 2816]], "Ev Idx": 6352 + } + }, + { + "ph": "s", "id": 172, "pid": 4183440, "tid": 4183440, "ts": 667115404789.599, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115404861.924, "dur": 43.557, + "args": { + "External id": 227554,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115404920.010, "dur": 92.961, + "args": { + "External id": 227555,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115405022.470, "dur": 33.023, + "args": { + "External id": 227556,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115405064.745, "dur": 27.771, + "args": { + "External id": 227557,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115405116.728, "dur": 23.727, + "args": { + "External id": 227558,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 4183440, "tid": 4183440, + "ts": 667115405157.620, "dur": 13.358, + "args": { + "External id": 227559,"kernel_hash": "cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "16", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/l2/cl2wm4hba2dd5vb7b2xth2batzpjiesxlywgh5etvvp6c2wd7rk5.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115405189.169, "dur": 123.774, + "args": { + "External id": 227560,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115405237.135, "dur": 11.590, + "args": { + "External id": 227561,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 6360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115405242.275, "dur": 5.715, + "args": { + "External id": 227562,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115405251.347, "dur": 4.206, + "args": { + "External id": 227563,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115405257.125, "dur": 2.046, + "args": { + "External id": 227564,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115405261.376, "dur": 2.891, + "args": { + "External id": 227565,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115405323.247, "dur": 40.804, + "args": { + "External id": 227566,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [1024, 1]], "Input Dims": [[65536, 1024], [1024, 1024], [65536, 1024]], "Ev Idx": 6365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 4183440, "tid": 4183440, + "ts": 667115405395.757, "dur": 27.244, + "args": { + "External id": 227567,"kernel_hash": "cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/nj/cnjbue7nf7gv2knx3zot7zn5kaxyrd3hc7qwdjvlhjrtvf774taj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1024, 1], [1024, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536, 1024], [1024], [65536, 1024], [65536, 1024], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115405430.798, "dur": 36.552, + "args": { + "External id": 227568,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 6367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115405476.335, "dur": 48.196, + "args": { + "External id": 227569,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024], [2816, 1]], "Input Dims": [[65536, 1024], [1024, 2816], [65536, 2816]], "Ev Idx": 6368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 4183440, "tid": 4183440, + "ts": 667115405550.572, "dur": 24.874, + "args": { + "External id": 227570,"kernel_hash": "cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp", "grid": "grid(184549376,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "184549376"], "kernel_file": "/tmp/torchinductor_cvm/w3/cw3skkho6yb4encoyp3h6ahhtvu5iazx6tllrwt6cabagzim3icp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2816, 1], [2816, 1], [11534336, 2816, 1], []], "Input Dims": [[65536, 2816], [65536, 2816], [16, 4096, 2816], []], "Ev Idx": 6369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115405582.210, "dur": 51.340, + "args": { + "External id": 227571,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816], [1024, 1]], "Input Dims": [[65536, 2816], [2816, 1024], [65536, 1024]], "Ev Idx": 6370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 4183440, "tid": 4183440, + "ts": 667115405686.449, "dur": 23.187, + "args": { + "External id": 227572,"kernel_hash": "cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x", "grid": "grid(67108864,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "67108864"], "kernel_file": "/tmp/torchinductor_cvm/pq/cpqzomrawiuklcctjbbwmvmzd7xgj2j22x55badf4x4gmk776f7x.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [65536, 1024], []], "Ev Idx": 6371 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.19)", "pid": 4183440, "tid": 4183440, + "ts": 667115405866.733, "dur": 32.804, + "args": { + "External id": 227573,"Record function id": 0, "Ev Idx": 6372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115405984.442, "dur": 264.323, + "args": { + "External id": 227574,"Sequence number": 2757785, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1], [], [], [], [], [], []], "Input Dims": [[16, 4096, 1024], [1024], [], [], [], [], [], []], "Ev Idx": 6373 + } + }, + { + "ph": "s", "id": 171, "pid": 4183440, "tid": 4183440, "ts": 667115405984.442, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115406012.746, "dur": 8.046, + "args": { + "External id": 227575,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115406015.105, "dur": 5.467, + "args": { + "External id": 227576,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115406030.799, "dur": 13.240, + "args": { + "External id": 227577,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 6376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115406034.192, "dur": 9.300, + "args": { + "External id": 227578,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115406050.902, "dur": 5.099, + "args": { + "External id": 227579,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115406229.241, "dur": 6.795, + "args": { + "External id": 227580,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115406233.083, "dur": 2.658, + "args": { + "External id": 227581,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115406278.048, "dur": 124.516, + "args": { + "External id": 227582,"Sequence number": 2757786, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [1024, 1024], []], "Ev Idx": 6381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115406281.165, "dur": 13.998, + "args": { + "External id": 227583,"Sequence number": 2757786, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 6382 + } + }, + { + "ph": "s", "id": 170, "pid": 4183440, "tid": 4183440, "ts": 667115406281.165, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115406286.891, "dur": 6.394, + "args": { + "External id": 227584,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 6383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115406290.819, "dur": 2.110, + "args": { + "External id": 227585,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 6384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115406298.423, "dur": 103.703, + "args": { + "External id": 227586,"Sequence number": 2757787, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 1024]], "Ev Idx": 6385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115406301.990, "dur": 4.944, + "args": { + "External id": 227587,"Sequence number": 2757787, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115406303.038, "dur": 3.746, + "args": { + "External id": 227588,"Sequence number": 2757787, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6387 + } + }, + { + "ph": "s", "id": 169, "pid": 4183440, "tid": 4183440, "ts": 667115406303.038, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115406309.591, "dur": 81.697, + "args": { + "External id": 227589,"Sequence number": 2757788, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 6388 + } + }, + { + "ph": "s", "id": 168, "pid": 4183440, "tid": 4183440, "ts": 667115406309.591, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115406395.033, "dur": 5.929, + "args": { + "External id": 227590,"Sequence number": 2757789, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6389 + } + }, + { + "ph": "s", "id": 167, "pid": 4183440, "tid": 4183440, "ts": 667115406395.033, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115406412.453, "dur": 65.273, + "args": { + "External id": 227591,"Sequence number": 2757790, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [1024, 1024], []], "Ev Idx": 6390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115406413.693, "dur": 7.509, + "args": { + "External id": 227592,"Sequence number": 2757790, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 6391 + } + }, + { + "ph": "s", "id": 166, "pid": 4183440, "tid": 4183440, "ts": 667115406413.693, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115406416.872, "dur": 3.268, + "args": { + "External id": 227593,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 6392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115406418.971, "dur": 0.915, + "args": { + "External id": 227594,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 6393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115406422.140, "dur": 55.314, + "args": { + "External id": 227595,"Sequence number": 2757791, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 1024]], "Ev Idx": 6394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115406423.239, "dur": 6.142, + "args": { + "External id": 227596,"Sequence number": 2757791, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115406424.359, "dur": 4.856, + "args": { + "External id": 227597,"Sequence number": 2757791, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6396 + } + }, + { + "ph": "s", "id": 165, "pid": 4183440, "tid": 4183440, "ts": 667115406424.359, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115406430.925, "dur": 39.481, + "args": { + "External id": 227598,"Sequence number": 2757792, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 6397 + } + }, + { + "ph": "s", "id": 164, "pid": 4183440, "tid": 4183440, "ts": 667115406430.925, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115406472.191, "dur": 4.813, + "args": { + "External id": 227599,"Sequence number": 2757793, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6398 + } + }, + { + "ph": "s", "id": 163, "pid": 4183440, "tid": 4183440, "ts": 667115406472.191, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115406484.844, "dur": 86.886, + "args": { + "External id": 227600,"Sequence number": 2757794, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [1024, 1024], []], "Ev Idx": 6399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115406485.929, "dur": 25.414, + "args": { + "External id": 227601,"Sequence number": 2757794, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 6400 + } + }, + { + "ph": "s", "id": 162, "pid": 4183440, "tid": 4183440, "ts": 667115406485.929, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115406488.849, "dur": 20.586, + "args": { + "External id": 227602,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 6401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115406507.790, "dur": 1.136, + "args": { + "External id": 227603,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 6402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115406512.868, "dur": 58.568, + "args": { + "External id": 227604,"Sequence number": 2757795, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 1024]], "Ev Idx": 6403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115406514.527, "dur": 6.160, + "args": { + "External id": 227605,"Sequence number": 2757795, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115406515.788, "dur": 4.753, + "args": { + "External id": 227606,"Sequence number": 2757795, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6405 + } + }, + { + "ph": "s", "id": 161, "pid": 4183440, "tid": 4183440, "ts": 667115406515.788, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115406521.477, "dur": 43.602, + "args": { + "External id": 227607,"Sequence number": 2757796, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 6406 + } + }, + { + "ph": "s", "id": 160, "pid": 4183440, "tid": 4183440, "ts": 667115406521.477, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115406567.133, "dur": 3.848, + "args": { + "External id": 227608,"Sequence number": 2757797, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6407 + } + }, + { + "ph": "s", "id": 159, "pid": 4183440, "tid": 4183440, "ts": 667115406567.133, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115406595.345, "dur": 4.899, + "args": { + "External id": 227609,"Sequence number": 2757798, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115406596.418, "dur": 3.666, + "args": { + "External id": 227610,"Sequence number": 2757798, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6409 + } + }, + { + "ph": "s", "id": 158, "pid": 4183440, "tid": 4183440, "ts": 667115406596.418, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115406610.544, "dur": 5.602, + "args": { + "External id": 227611,"Sequence number": 2757799, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115406611.559, "dur": 4.438, + "args": { + "External id": 227612,"Sequence number": 2757799, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6411 + } + }, + { + "ph": "s", "id": 157, "pid": 4183440, "tid": 4183440, "ts": 667115406611.559, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115406620.246, "dur": 3.644, + "args": { + "External id": 227613,"Sequence number": 2757800, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115406621.630, "dur": 2.029, + "args": { + "External id": 227614,"Sequence number": 2757800, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6413 + } + }, + { + "ph": "s", "id": 156, "pid": 4183440, "tid": 4183440, "ts": 667115406621.630, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115406695.547, "dur": 191.870, + "args": { + "External id": 227615,"Sequence number": 2757801, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 6414 + } + }, + { + "ph": "s", "id": 155, "pid": 4183440, "tid": 4183440, "ts": 667115406695.547, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115406721.532, "dur": 10.175, + "args": { + "External id": 227616,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 6415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115406724.713, "dur": 6.388, + "args": { + "External id": 227617,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115406903.703, "dur": 110.993, + "args": { + "External id": 227618,"Sequence number": 2757802, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 6417 + } + }, + { + "ph": "s", "id": 154, "pid": 4183440, "tid": 4183440, "ts": 667115406903.703, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115406917.691, "dur": 8.718, + "args": { + "External id": 227619,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 6418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115406920.110, "dur": 5.963, + "args": { + "External id": 227620,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 4183440, "tid": 4183440, + "ts": 667115407045.824, "dur": 183.700, + "args": { + "External id": 227621,"Sequence number": 2757803, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], []], "Ev Idx": 6420 + } + }, + { + "ph": "s", "id": 153, "pid": 4183440, "tid": 4183440, "ts": 667115407045.824, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115407075.990, "dur": 127.153, + "args": { + "External id": 227622,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115407126.518, "dur": 7.408, + "args": { + "External id": 227623,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 6422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115407128.718, "dur": 4.675, + "args": { + "External id": 227624,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115407136.763, "dur": 4.365, + "args": { + "External id": 227625,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115407142.580, "dur": 1.352, + "args": { + "External id": 227626,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115407146.634, "dur": 5.025, + "args": { + "External id": 227627,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 4183440, "tid": 4183440, + "ts": 667115407216.383, "dur": 5.214, + "args": { + "External id": 227628,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 6427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115407234.773, "dur": 6.917, + "args": { + "External id": 227629,"Sequence number": 2757804, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 6428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115407236.713, "dur": 4.811, + "args": { + "External id": 227630,"Sequence number": 2757804, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 6429 + } + }, + { + "ph": "s", "id": 152, "pid": 4183440, "tid": 4183440, "ts": 667115407236.713, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115407255.400, "dur": 106.782, + "args": { + "External id": 227631,"Sequence number": 2757805, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [1024, 1024], []], "Ev Idx": 6430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115407256.983, "dur": 9.444, + "args": { + "External id": 227632,"Sequence number": 2757805, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 6431 + } + }, + { + "ph": "s", "id": 151, "pid": 4183440, "tid": 4183440, "ts": 667115407256.983, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115407260.266, "dur": 4.961, + "args": { + "External id": 227633,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 6432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115407263.236, "dur": 1.757, + "args": { + "External id": 227634,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 6433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115407268.344, "dur": 93.376, + "args": { + "External id": 227635,"Sequence number": 2757806, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 1024]], "Ev Idx": 6434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115407270.891, "dur": 5.504, + "args": { + "External id": 227636,"Sequence number": 2757806, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115407271.990, "dur": 4.271, + "args": { + "External id": 227637,"Sequence number": 2757806, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6436 + } + }, + { + "ph": "s", "id": 150, "pid": 4183440, "tid": 4183440, "ts": 667115407271.990, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115407277.772, "dur": 77.850, + "args": { + "External id": 227638,"Sequence number": 2757807, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 6437 + } + }, + { + "ph": "s", "id": 149, "pid": 4183440, "tid": 4183440, "ts": 667115407277.772, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115407357.999, "dur": 3.056, + "args": { + "External id": 227639,"Sequence number": 2757808, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6438 + } + }, + { + "ph": "s", "id": 148, "pid": 4183440, "tid": 4183440, "ts": 667115407357.999, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115407397.288, "dur": 245.517, + "args": { + "External id": 227640,"Sequence number": 2757809, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1], [], [4194304, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 1024], [1024], [], [16, 4096, 1024], [], [], [], []], "Ev Idx": 6439 + } + }, + { + "ph": "s", "id": 147, "pid": 4183440, "tid": 4183440, "ts": 667115407397.288, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115407414.233, "dur": 3.355, + "args": { + "External id": 227641,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115407416.001, "dur": 1.452, + "args": { + "External id": 227642,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 4183440, "tid": 4183440, + "ts": 667115407423.126, "dur": 3.943, + "args": { + "External id": 227643,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1024, 1]], "Input Dims": [[16, 4096, 1024], [65536, 1024]], "Ev Idx": 6442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115407424.632, "dur": 2.333, + "args": { + "External id": 227644,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115407425.690, "dur": 1.160, + "args": { + "External id": 227645,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115407434.422, "dur": 6.774, + "args": { + "External id": 227646,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 6445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115407436.439, "dur": 4.453, + "args": { + "External id": 227647,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115407448.287, "dur": 3.594, + "args": { + "External id": 227648,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115407455.869, "dur": 5.245, + "args": { + "External id": 227649,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115407617.922, "dur": 6.096, + "args": { + "External id": 227650,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115407619.106, "dur": 4.553, + "args": { + "External id": 227651,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115407627.004, "dur": 2.734, + "args": { + "External id": 227652,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115407628.325, "dur": 1.304, + "args": { + "External id": 227653,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115407701.815, "dur": 122.410, + "args": { + "External id": 227654,"Sequence number": 2757810, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [2816, 1024], []], "Ev Idx": 6453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115407703.317, "dur": 10.578, + "args": { + "External id": 227655,"Sequence number": 2757810, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 6454 + } + }, + { + "ph": "s", "id": 146, "pid": 4183440, "tid": 4183440, "ts": 667115407703.317, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115407706.866, "dur": 5.425, + "args": { + "External id": 227656,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 6455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115407709.979, "dur": 1.916, + "args": { + "External id": 227657,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 6456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115407715.539, "dur": 108.414, + "args": { + "External id": 227658,"Sequence number": 2757811, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 2816]], "Ev Idx": 6457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115407717.601, "dur": 6.960, + "args": { + "External id": 227659,"Sequence number": 2757811, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115407718.945, "dur": 5.478, + "args": { + "External id": 227660,"Sequence number": 2757811, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6459 + } + }, + { + "ph": "s", "id": 145, "pid": 4183440, "tid": 4183440, "ts": 667115407718.945, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115407725.458, "dur": 92.769, + "args": { + "External id": 227661,"Sequence number": 2757812, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 2816]], "Ev Idx": 6460 + } + }, + { + "ph": "s", "id": 144, "pid": 4183440, "tid": 4183440, "ts": 667115407725.458, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115407820.678, "dur": 2.616, + "args": { + "External id": 227662,"Sequence number": 2757813, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1], []], "Input Dims": [[65536, 2816], []], "Ev Idx": 6461 + } + }, + { + "ph": "s", "id": 143, "pid": 4183440, "tid": 4183440, "ts": 667115407820.678, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115407833.216, "dur": 67.094, + "args": { + "External id": 227663,"Sequence number": 2757814, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [2816, 1024], []], "Ev Idx": 6462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115407834.099, "dur": 8.388, + "args": { + "External id": 227664,"Sequence number": 2757814, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 6463 + } + }, + { + "ph": "s", "id": 142, "pid": 4183440, "tid": 4183440, "ts": 667115407834.099, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115407835.534, "dur": 5.713, + "args": { + "External id": 227665,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 6464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115407840.127, "dur": 0.920, + "args": { + "External id": 227666,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 6465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115407843.156, "dur": 56.926, + "args": { + "External id": 227667,"Sequence number": 2757815, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 2816]], "Ev Idx": 6466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115407844.498, "dur": 4.893, + "args": { + "External id": 227668,"Sequence number": 2757815, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115407845.415, "dur": 3.834, + "args": { + "External id": 227669,"Sequence number": 2757815, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6468 + } + }, + { + "ph": "s", "id": 141, "pid": 4183440, "tid": 4183440, "ts": 667115407845.415, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115407850.053, "dur": 43.905, + "args": { + "External id": 227670,"Sequence number": 2757816, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 2816]], "Ev Idx": 6469 + } + }, + { + "ph": "s", "id": 140, "pid": 4183440, "tid": 4183440, "ts": 667115407850.053, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115407895.597, "dur": 4.020, + "args": { + "External id": 227671,"Sequence number": 2757817, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1], []], "Input Dims": [[65536, 2816], []], "Ev Idx": 6470 + } + }, + { + "ph": "s", "id": 139, "pid": 4183440, "tid": 4183440, "ts": 667115407895.597, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115407922.017, "dur": 154.859, + "args": { + "External id": 227672,"Sequence number": 2757818, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[11534336, 2816, 1], [11534336, 2816, 1], [2816, 1], []], "Input Dims": [[16, 4096, 2816], [16, 4096, 2816], [1024, 2816], []], "Ev Idx": 6471 + } + }, + { + "ph": "s", "id": 138, "pid": 4183440, "tid": 4183440, "ts": 667115407922.017, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115407967.408, "dur": 4.219, + "args": { + "External id": 227673,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2816]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115408008.454, "dur": 54.009, + "args": { + "External id": 227674,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[11534336, 2816, 1], [2816, 1], []], "Input Dims": [[16, 4096, 2816], [1024, 2816], []], "Ev Idx": 6473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115408009.474, "dur": 4.734, + "args": { + "External id": 227675,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 6474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115408010.690, "dur": 2.668, + "args": { + "External id": 227676,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2816, 1], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 6475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115408012.310, "dur": 0.815, + "args": { + "External id": 227677,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 6476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115408014.934, "dur": 47.119, + "args": { + "External id": 227678,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[11534336, 2816, 1], [1, 2816]], "Input Dims": [[16, 4096, 2816], [2816, 1024]], "Ev Idx": 6477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115408016.572, "dur": 2.286, + "args": { + "External id": 227679,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 6478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115408017.332, "dur": 1.336, + "args": { + "External id": 227680,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 6479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115408019.619, "dur": 38.853, + "args": { + "External id": 227681,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816]], "Input Dims": [[65536, 2816], [2816, 1024]], "Ev Idx": 6480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115408060.370, "dur": 1.124, + "args": { + "External id": 227682,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 4183440, "tid": 4183440, + "ts": 667115408086.995, "dur": 28.201, + "args": { + "External id": 227683,"Sequence number": 2757819, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 6482 + } + }, + { + "ph": "s", "id": 137, "pid": 4183440, "tid": 4183440, "ts": 667115408086.995, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115408151.660, "dur": 183.317, + "args": { + "External id": 227684,"Sequence number": 2757820, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1], [], [], [], [], [], []], "Input Dims": [[16, 4096, 1024], [1024], [], [], [], [], [], []], "Ev Idx": 6483 + } + }, + { + "ph": "s", "id": 136, "pid": 4183440, "tid": 4183440, "ts": 667115408151.660, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115408171.640, "dur": 3.558, + "args": { + "External id": 227685,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115408173.170, "dur": 1.860, + "args": { + "External id": 227686,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115408183.198, "dur": 7.523, + "args": { + "External id": 227687,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 6486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115408185.683, "dur": 4.714, + "args": { + "External id": 227688,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115408196.943, "dur": 3.407, + "args": { + "External id": 227689,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115408320.702, "dur": 4.939, + "args": { + "External id": 227690,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115408323.893, "dur": 1.531, + "args": { + "External id": 227691,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115408354.300, "dur": 76.283, + "args": { + "External id": 227692,"Sequence number": 2757821, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [1024, 1024], []], "Ev Idx": 6491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115408355.301, "dur": 7.399, + "args": { + "External id": 227693,"Sequence number": 2757821, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 6492 + } + }, + { + "ph": "s", "id": 135, "pid": 4183440, "tid": 4183440, "ts": 667115408355.301, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115408357.747, "dur": 3.836, + "args": { + "External id": 227694,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 6493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115408360.036, "dur": 1.331, + "args": { + "External id": 227695,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 6494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115408364.009, "dur": 66.279, + "args": { + "External id": 227696,"Sequence number": 2757822, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 1024]], "Ev Idx": 6495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115408366.064, "dur": 3.997, + "args": { + "External id": 227697,"Sequence number": 2757822, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115408367.353, "dur": 2.573, + "args": { + "External id": 227698,"Sequence number": 2757822, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6497 + } + }, + { + "ph": "s", "id": 134, "pid": 4183440, "tid": 4183440, "ts": 667115408367.353, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115408370.915, "dur": 54.377, + "args": { + "External id": 227699,"Sequence number": 2757823, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 6498 + } + }, + { + "ph": "s", "id": 133, "pid": 4183440, "tid": 4183440, "ts": 667115408370.915, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115408427.088, "dur": 2.691, + "args": { + "External id": 227700,"Sequence number": 2757824, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6499 + } + }, + { + "ph": "s", "id": 132, "pid": 4183440, "tid": 4183440, "ts": 667115408427.088, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115408437.698, "dur": 85.487, + "args": { + "External id": 227701,"Sequence number": 2757825, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [1024, 1024], []], "Ev Idx": 6500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115408438.657, "dur": 7.653, + "args": { + "External id": 227702,"Sequence number": 2757825, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 6501 + } + }, + { + "ph": "s", "id": 131, "pid": 4183440, "tid": 4183440, "ts": 667115408438.657, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115408442.687, "dur": 2.587, + "args": { + "External id": 227703,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 6502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115408444.392, "dur": 0.733, + "args": { + "External id": 227704,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 6503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115408447.489, "dur": 75.389, + "args": { + "External id": 227705,"Sequence number": 2757826, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 1024]], "Ev Idx": 6504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115408449.207, "dur": 5.661, + "args": { + "External id": 227706,"Sequence number": 2757826, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115408450.214, "dur": 4.480, + "args": { + "External id": 227707,"Sequence number": 2757826, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6506 + } + }, + { + "ph": "s", "id": 130, "pid": 4183440, "tid": 4183440, "ts": 667115408450.214, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115408455.724, "dur": 59.094, + "args": { + "External id": 227708,"Sequence number": 2757827, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 6507 + } + }, + { + "ph": "s", "id": 129, "pid": 4183440, "tid": 4183440, "ts": 667115408455.724, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115408517.400, "dur": 4.861, + "args": { + "External id": 227709,"Sequence number": 2757828, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6508 + } + }, + { + "ph": "s", "id": 128, "pid": 4183440, "tid": 4183440, "ts": 667115408517.400, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115408531.682, "dur": 62.607, + "args": { + "External id": 227710,"Sequence number": 2757829, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [1024, 1024], []], "Ev Idx": 6509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115408532.622, "dur": 7.086, + "args": { + "External id": 227711,"Sequence number": 2757829, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 6510 + } + }, + { + "ph": "s", "id": 127, "pid": 4183440, "tid": 4183440, "ts": 667115408532.622, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115408535.162, "dur": 3.373, + "args": { + "External id": 227712,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 6511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115408537.389, "dur": 1.000, + "args": { + "External id": 227713,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 6512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115408540.742, "dur": 53.317, + "args": { + "External id": 227714,"Sequence number": 2757830, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 1024]], "Ev Idx": 6513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115408541.738, "dur": 4.863, + "args": { + "External id": 227715,"Sequence number": 2757830, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115408542.970, "dur": 3.484, + "args": { + "External id": 227716,"Sequence number": 2757830, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6515 + } + }, + { + "ph": "s", "id": 126, "pid": 4183440, "tid": 4183440, "ts": 667115408542.970, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115408547.413, "dur": 41.275, + "args": { + "External id": 227717,"Sequence number": 2757831, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 6516 + } + }, + { + "ph": "s", "id": 125, "pid": 4183440, "tid": 4183440, "ts": 667115408547.413, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115408590.138, "dur": 3.288, + "args": { + "External id": 227718,"Sequence number": 2757832, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6517 + } + }, + { + "ph": "s", "id": 124, "pid": 4183440, "tid": 4183440, "ts": 667115408590.138, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115408610.142, "dur": 4.336, + "args": { + "External id": 227719,"Sequence number": 2757833, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115408611.318, "dur": 3.020, + "args": { + "External id": 227720,"Sequence number": 2757833, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6519 + } + }, + { + "ph": "s", "id": 123, "pid": 4183440, "tid": 4183440, "ts": 667115408611.318, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115408620.951, "dur": 5.539, + "args": { + "External id": 227721,"Sequence number": 2757834, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115408622.453, "dur": 3.918, + "args": { + "External id": 227722,"Sequence number": 2757834, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6521 + } + }, + { + "ph": "s", "id": 122, "pid": 4183440, "tid": 4183440, "ts": 667115408622.453, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115408630.947, "dur": 4.817, + "args": { + "External id": 227723,"Sequence number": 2757835, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115408631.795, "dur": 3.832, + "args": { + "External id": 227724,"Sequence number": 2757835, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6523 + } + }, + { + "ph": "s", "id": 121, "pid": 4183440, "tid": 4183440, "ts": 667115408631.795, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115408701.666, "dur": 155.253, + "args": { + "External id": 227725,"Sequence number": 2757836, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 6524 + } + }, + { + "ph": "s", "id": 120, "pid": 4183440, "tid": 4183440, "ts": 667115408701.666, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115408721.927, "dur": 9.665, + "args": { + "External id": 227726,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 6525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115408724.735, "dur": 6.349, + "args": { + "External id": 227727,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115408868.775, "dur": 99.441, + "args": { + "External id": 227728,"Sequence number": 2757837, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 6527 + } + }, + { + "ph": "s", "id": 119, "pid": 4183440, "tid": 4183440, "ts": 667115408868.775, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115408881.017, "dur": 7.086, + "args": { + "External id": 227729,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 6528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115408882.952, "dur": 4.795, + "args": { + "External id": 227730,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 4183440, "tid": 4183440, + "ts": 667115408995.816, "dur": 172.899, + "args": { + "External id": 227731,"Sequence number": 2757838, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], []], "Ev Idx": 6530 + } + }, + { + "ph": "s", "id": 118, "pid": 4183440, "tid": 4183440, "ts": 667115408995.816, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115409021.117, "dur": 123.587, + "args": { + "External id": 227732,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115409069.680, "dur": 7.648, + "args": { + "External id": 227733,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 6532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115409072.226, "dur": 4.487, + "args": { + "External id": 227734,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115409079.920, "dur": 4.476, + "args": { + "External id": 227735,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115409085.867, "dur": 1.669, + "args": { + "External id": 227736,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115409092.184, "dur": 3.426, + "args": { + "External id": 227737,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 4183440, "tid": 4183440, + "ts": 667115409155.419, "dur": 4.539, + "args": { + "External id": 227738,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 6537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115409173.816, "dur": 6.274, + "args": { + "External id": 227739,"Sequence number": 2757839, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 6538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115409175.388, "dur": 4.549, + "args": { + "External id": 227740,"Sequence number": 2757839, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 6539 + } + }, + { + "ph": "s", "id": 117, "pid": 4183440, "tid": 4183440, "ts": 667115409175.388, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115409192.621, "dur": 108.716, + "args": { + "External id": 227741,"Sequence number": 2757840, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [1024, 1024], []], "Ev Idx": 6540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115409193.846, "dur": 9.144, + "args": { + "External id": 227742,"Sequence number": 2757840, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 6541 + } + }, + { + "ph": "s", "id": 116, "pid": 4183440, "tid": 4183440, "ts": 667115409193.846, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115409197.185, "dur": 4.841, + "args": { + "External id": 227743,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 6542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115409200.176, "dur": 1.563, + "args": { + "External id": 227744,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 6543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115409204.621, "dur": 96.402, + "args": { + "External id": 227745,"Sequence number": 2757841, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 1024]], "Ev Idx": 6544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115409207.249, "dur": 3.422, + "args": { + "External id": 227746,"Sequence number": 2757841, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115409208.223, "dur": 2.311, + "args": { + "External id": 227747,"Sequence number": 2757841, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6546 + } + }, + { + "ph": "s", "id": 115, "pid": 4183440, "tid": 4183440, "ts": 667115409208.223, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115409212.053, "dur": 82.160, + "args": { + "External id": 227748,"Sequence number": 2757842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 6547 + } + }, + { + "ph": "s", "id": 114, "pid": 4183440, "tid": 4183440, "ts": 667115409212.053, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115409296.820, "dur": 3.460, + "args": { + "External id": 227749,"Sequence number": 2757843, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6548 + } + }, + { + "ph": "s", "id": 113, "pid": 4183440, "tid": 4183440, "ts": 667115409296.820, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115409334.109, "dur": 232.757, + "args": { + "External id": 227750,"Sequence number": 2757844, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1], [], [4194304, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 1024], [1024], [], [16, 4096, 1024], [], [], [], []], "Ev Idx": 6549 + } + }, + { + "ph": "s", "id": 112, "pid": 4183440, "tid": 4183440, "ts": 667115409334.109, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115409353.283, "dur": 3.409, + "args": { + "External id": 227751,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115409355.263, "dur": 1.294, + "args": { + "External id": 227752,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 4183440, "tid": 4183440, + "ts": 667115409361.423, "dur": 3.727, + "args": { + "External id": 227753,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1024, 1]], "Input Dims": [[16, 4096, 1024], [65536, 1024]], "Ev Idx": 6552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115409363.092, "dur": 1.951, + "args": { + "External id": 227754,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115409364.143, "dur": 0.796, + "args": { + "External id": 227755,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115409372.549, "dur": 6.454, + "args": { + "External id": 227756,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 6555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115409374.646, "dur": 4.001, + "args": { + "External id": 227757,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115409385.355, "dur": 2.710, + "args": { + "External id": 227758,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115409391.853, "dur": 3.002, + "args": { + "External id": 227759,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115409541.637, "dur": 6.882, + "args": { + "External id": 227760,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115409545.342, "dur": 2.636, + "args": { + "External id": 227761,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115409551.337, "dur": 2.896, + "args": { + "External id": 227762,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115409552.885, "dur": 1.229, + "args": { + "External id": 227763,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115409587.487, "dur": 157.469, + "args": { + "External id": 227764,"Sequence number": 2757845, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [2816, 1024], []], "Ev Idx": 6563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115409588.627, "dur": 7.559, + "args": { + "External id": 227765,"Sequence number": 2757845, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 6564 + } + }, + { + "ph": "s", "id": 111, "pid": 4183440, "tid": 4183440, "ts": 667115409588.627, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115409591.314, "dur": 3.925, + "args": { + "External id": 227766,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 6565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115409593.501, "dur": 1.454, + "args": { + "External id": 227767,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 6566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115409597.369, "dur": 147.282, + "args": { + "External id": 227768,"Sequence number": 2757846, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 2816]], "Ev Idx": 6567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115409599.299, "dur": 6.071, + "args": { + "External id": 227769,"Sequence number": 2757846, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115409600.717, "dur": 4.503, + "args": { + "External id": 227770,"Sequence number": 2757846, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6569 + } + }, + { + "ph": "s", "id": 110, "pid": 4183440, "tid": 4183440, "ts": 667115409600.717, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115409606.235, "dur": 112.751, + "args": { + "External id": 227771,"Sequence number": 2757847, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 2816]], "Ev Idx": 6570 + } + }, + { + "ph": "s", "id": 109, "pid": 4183440, "tid": 4183440, "ts": 667115409606.235, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115409737.648, "dur": 6.183, + "args": { + "External id": 227772,"Sequence number": 2757848, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1], []], "Input Dims": [[65536, 2816], []], "Ev Idx": 6571 + } + }, + { + "ph": "s", "id": 108, "pid": 4183440, "tid": 4183440, "ts": 667115409737.648, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115409757.189, "dur": 73.976, + "args": { + "External id": 227773,"Sequence number": 2757849, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [2816, 1024], []], "Ev Idx": 6572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115409758.146, "dur": 7.342, + "args": { + "External id": 227774,"Sequence number": 2757849, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 6573 + } + }, + { + "ph": "s", "id": 107, "pid": 4183440, "tid": 4183440, "ts": 667115409758.146, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115409760.240, "dur": 3.896, + "args": { + "External id": 227775,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 6574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115409762.231, "dur": 1.490, + "args": { + "External id": 227776,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 6575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115409766.069, "dur": 64.821, + "args": { + "External id": 227777,"Sequence number": 2757850, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 2816]], "Ev Idx": 6576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115409767.950, "dur": 5.190, + "args": { + "External id": 227778,"Sequence number": 2757850, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115409768.951, "dur": 4.029, + "args": { + "External id": 227779,"Sequence number": 2757850, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6578 + } + }, + { + "ph": "s", "id": 106, "pid": 4183440, "tid": 4183440, "ts": 667115409768.951, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115409773.975, "dur": 52.367, + "args": { + "External id": 227780,"Sequence number": 2757851, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 2816]], "Ev Idx": 6579 + } + }, + { + "ph": "s", "id": 105, "pid": 4183440, "tid": 4183440, "ts": 667115409773.975, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115409828.181, "dur": 2.225, + "args": { + "External id": 227781,"Sequence number": 2757852, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1], []], "Input Dims": [[65536, 2816], []], "Ev Idx": 6580 + } + }, + { + "ph": "s", "id": 104, "pid": 4183440, "tid": 4183440, "ts": 667115409828.181, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115409857.400, "dur": 154.372, + "args": { + "External id": 227782,"Sequence number": 2757853, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[11534336, 2816, 1], [11534336, 2816, 1], [2816, 1], []], "Input Dims": [[16, 4096, 2816], [16, 4096, 2816], [1024, 2816], []], "Ev Idx": 6581 + } + }, + { + "ph": "s", "id": 103, "pid": 4183440, "tid": 4183440, "ts": 667115409857.400, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115409897.185, "dur": 5.025, + "args": { + "External id": 227783,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2816]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115409933.097, "dur": 64.527, + "args": { + "External id": 227784,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[11534336, 2816, 1], [2816, 1], []], "Input Dims": [[16, 4096, 2816], [1024, 2816], []], "Ev Idx": 6583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115409933.845, "dur": 7.034, + "args": { + "External id": 227785,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 6584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115409935.090, "dur": 4.947, + "args": { + "External id": 227786,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2816, 1], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 6585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115409939.261, "dur": 0.603, + "args": { + "External id": 227787,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 6586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115409941.846, "dur": 55.411, + "args": { + "External id": 227788,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[11534336, 2816, 1], [1, 2816]], "Input Dims": [[16, 4096, 2816], [2816, 1024]], "Ev Idx": 6587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115409943.820, "dur": 2.653, + "args": { + "External id": 227789,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 6588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115409945.156, "dur": 1.211, + "args": { + "External id": 227790,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 6589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115409947.427, "dur": 46.549, + "args": { + "External id": 227791,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816]], "Input Dims": [[65536, 2816], [2816, 1024]], "Ev Idx": 6590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115409995.703, "dur": 0.998, + "args": { + "External id": 227792,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 4183440, "tid": 4183440, + "ts": 667115410020.325, "dur": 25.726, + "args": { + "External id": 227793,"Sequence number": 2757854, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 6592 + } + }, + { + "ph": "s", "id": 102, "pid": 4183440, "tid": 4183440, "ts": 667115410020.325, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115410081.230, "dur": 186.140, + "args": { + "External id": 227794,"Sequence number": 2757855, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1], [], [], [], [], [], []], "Input Dims": [[16, 4096, 1024], [1024], [], [], [], [], [], []], "Ev Idx": 6593 + } + }, + { + "ph": "s", "id": 101, "pid": 4183440, "tid": 4183440, "ts": 667115410081.230, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115410099.829, "dur": 3.117, + "args": { + "External id": 227795,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115410100.864, "dur": 1.875, + "args": { + "External id": 227796,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115410111.368, "dur": 7.643, + "args": { + "External id": 227797,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 6596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115410114.222, "dur": 4.444, + "args": { + "External id": 227798,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115410124.987, "dur": 3.190, + "args": { + "External id": 227799,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115410253.016, "dur": 2.969, + "args": { + "External id": 227800,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115410254.048, "dur": 1.773, + "args": { + "External id": 227801,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115410286.311, "dur": 79.336, + "args": { + "External id": 227802,"Sequence number": 2757856, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [1024, 1024], []], "Ev Idx": 6601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115410287.141, "dur": 7.137, + "args": { + "External id": 227803,"Sequence number": 2757856, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 6602 + } + }, + { + "ph": "s", "id": 100, "pid": 4183440, "tid": 4183440, "ts": 667115410287.141, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115410289.601, "dur": 3.372, + "args": { + "External id": 227804,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 6603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115410291.729, "dur": 1.050, + "args": { + "External id": 227805,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 6604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115410295.657, "dur": 69.663, + "args": { + "External id": 227806,"Sequence number": 2757857, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 1024]], "Ev Idx": 6605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115410297.199, "dur": 4.194, + "args": { + "External id": 227807,"Sequence number": 2757857, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115410298.390, "dur": 2.844, + "args": { + "External id": 227808,"Sequence number": 2757857, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6607 + } + }, + { + "ph": "s", "id": 99, "pid": 4183440, "tid": 4183440, "ts": 667115410298.390, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115410302.384, "dur": 53.120, + "args": { + "External id": 227809,"Sequence number": 2757858, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 6608 + } + }, + { + "ph": "s", "id": 98, "pid": 4183440, "tid": 4183440, "ts": 667115410302.384, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115410357.703, "dur": 6.998, + "args": { + "External id": 227810,"Sequence number": 2757859, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6609 + } + }, + { + "ph": "s", "id": 97, "pid": 4183440, "tid": 4183440, "ts": 667115410357.703, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115410373.725, "dur": 63.182, + "args": { + "External id": 227811,"Sequence number": 2757860, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [1024, 1024], []], "Ev Idx": 6610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115410374.421, "dur": 7.437, + "args": { + "External id": 227812,"Sequence number": 2757860, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 6611 + } + }, + { + "ph": "s", "id": 96, "pid": 4183440, "tid": 4183440, "ts": 667115410374.421, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115410377.047, "dur": 3.443, + "args": { + "External id": 227813,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 6612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115410379.204, "dur": 1.113, + "args": { + "External id": 227814,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 6613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115410382.881, "dur": 53.742, + "args": { + "External id": 227815,"Sequence number": 2757861, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 1024]], "Ev Idx": 6614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115410383.980, "dur": 4.545, + "args": { + "External id": 227816,"Sequence number": 2757861, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115410385.578, "dur": 2.787, + "args": { + "External id": 227817,"Sequence number": 2757861, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6616 + } + }, + { + "ph": "s", "id": 95, "pid": 4183440, "tid": 4183440, "ts": 667115410385.578, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115410389.676, "dur": 42.622, + "args": { + "External id": 227818,"Sequence number": 2757862, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 6617 + } + }, + { + "ph": "s", "id": 94, "pid": 4183440, "tid": 4183440, "ts": 667115410389.676, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115410433.856, "dur": 2.445, + "args": { + "External id": 227819,"Sequence number": 2757863, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6618 + } + }, + { + "ph": "s", "id": 93, "pid": 4183440, "tid": 4183440, "ts": 667115410433.856, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115410443.266, "dur": 77.146, + "args": { + "External id": 227820,"Sequence number": 2757864, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [1024, 1024], []], "Ev Idx": 6619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115410444.023, "dur": 5.983, + "args": { + "External id": 227821,"Sequence number": 2757864, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 6620 + } + }, + { + "ph": "s", "id": 92, "pid": 4183440, "tid": 4183440, "ts": 667115410444.023, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115410445.785, "dur": 2.982, + "args": { + "External id": 227822,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 6621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115410447.739, "dur": 0.907, + "args": { + "External id": 227823,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 6622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115410450.889, "dur": 69.310, + "args": { + "External id": 227824,"Sequence number": 2757865, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 1024]], "Ev Idx": 6623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115410451.956, "dur": 5.103, + "args": { + "External id": 227825,"Sequence number": 2757865, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115410453.185, "dur": 3.733, + "args": { + "External id": 227826,"Sequence number": 2757865, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6625 + } + }, + { + "ph": "s", "id": 91, "pid": 4183440, "tid": 4183440, "ts": 667115410453.185, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115410457.731, "dur": 56.791, + "args": { + "External id": 227827,"Sequence number": 2757866, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 6626 + } + }, + { + "ph": "s", "id": 90, "pid": 4183440, "tid": 4183440, "ts": 667115410457.731, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115410517.276, "dur": 2.453, + "args": { + "External id": 227828,"Sequence number": 2757867, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6627 + } + }, + { + "ph": "s", "id": 89, "pid": 4183440, "tid": 4183440, "ts": 667115410517.276, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115410537.271, "dur": 4.415, + "args": { + "External id": 227829,"Sequence number": 2757868, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115410538.551, "dur": 2.999, + "args": { + "External id": 227830,"Sequence number": 2757868, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6629 + } + }, + { + "ph": "s", "id": 88, "pid": 4183440, "tid": 4183440, "ts": 667115410538.551, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115410548.045, "dur": 5.890, + "args": { + "External id": 227831,"Sequence number": 2757869, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115410549.088, "dur": 4.677, + "args": { + "External id": 227832,"Sequence number": 2757869, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6631 + } + }, + { + "ph": "s", "id": 87, "pid": 4183440, "tid": 4183440, "ts": 667115410549.088, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115410558.465, "dur": 3.949, + "args": { + "External id": 227833,"Sequence number": 2757870, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115410559.536, "dur": 2.539, + "args": { + "External id": 227834,"Sequence number": 2757870, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6633 + } + }, + { + "ph": "s", "id": 86, "pid": 4183440, "tid": 4183440, "ts": 667115410559.536, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115410592.359, "dur": 200.913, + "args": { + "External id": 227835,"Sequence number": 2757871, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 6634 + } + }, + { + "ph": "s", "id": 85, "pid": 4183440, "tid": 4183440, "ts": 667115410592.359, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115410612.649, "dur": 8.643, + "args": { + "External id": 227836,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 6635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115410615.102, "dur": 5.799, + "args": { + "External id": 227837,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115410807.666, "dur": 108.200, + "args": { + "External id": 227838,"Sequence number": 2757872, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 6637 + } + }, + { + "ph": "s", "id": 84, "pid": 4183440, "tid": 4183440, "ts": 667115410807.666, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115410820.922, "dur": 8.318, + "args": { + "External id": 227839,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 6638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115410823.489, "dur": 5.309, + "args": { + "External id": 227840,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 4183440, "tid": 4183440, + "ts": 667115410970.710, "dur": 174.004, + "args": { + "External id": 227841,"Sequence number": 2757873, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], []], "Ev Idx": 6640 + } + }, + { + "ph": "s", "id": 83, "pid": 4183440, "tid": 4183440, "ts": 667115410970.710, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115410995.421, "dur": 125.451, + "args": { + "External id": 227842,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115411043.419, "dur": 10.074, + "args": { + "External id": 227843,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 6642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115411045.774, "dur": 6.998, + "args": { + "External id": 227844,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115411058.070, "dur": 4.488, + "args": { + "External id": 227845,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115411063.864, "dur": 1.660, + "args": { + "External id": 227846,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115411068.137, "dur": 3.183, + "args": { + "External id": 227847,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 4183440, "tid": 4183440, + "ts": 667115411131.415, "dur": 4.838, + "args": { + "External id": 227848,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 6647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115411149.500, "dur": 5.647, + "args": { + "External id": 227849,"Sequence number": 2757874, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 6648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115411150.839, "dur": 4.186, + "args": { + "External id": 227850,"Sequence number": 2757874, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 6649 + } + }, + { + "ph": "s", "id": 82, "pid": 4183440, "tid": 4183440, "ts": 667115411150.839, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115411166.924, "dur": 108.446, + "args": { + "External id": 227851,"Sequence number": 2757875, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [1024, 1024], []], "Ev Idx": 6650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115411168.130, "dur": 11.036, + "args": { + "External id": 227852,"Sequence number": 2757875, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 6651 + } + }, + { + "ph": "s", "id": 81, "pid": 4183440, "tid": 4183440, "ts": 667115411168.130, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115411173.540, "dur": 4.564, + "args": { + "External id": 227853,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 6652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115411176.362, "dur": 1.500, + "args": { + "External id": 227854,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 6653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115411180.243, "dur": 94.768, + "args": { + "External id": 227855,"Sequence number": 2757876, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 1024]], "Ev Idx": 6654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115411182.341, "dur": 3.387, + "args": { + "External id": 227856,"Sequence number": 2757876, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115411183.151, "dur": 2.429, + "args": { + "External id": 227857,"Sequence number": 2757876, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6656 + } + }, + { + "ph": "s", "id": 80, "pid": 4183440, "tid": 4183440, "ts": 667115411183.151, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115411186.640, "dur": 79.636, + "args": { + "External id": 227858,"Sequence number": 2757877, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 6657 + } + }, + { + "ph": "s", "id": 79, "pid": 4183440, "tid": 4183440, "ts": 667115411186.640, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115411268.825, "dur": 5.487, + "args": { + "External id": 227859,"Sequence number": 2757878, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6658 + } + }, + { + "ph": "s", "id": 78, "pid": 4183440, "tid": 4183440, "ts": 667115411268.825, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115411306.600, "dur": 212.179, + "args": { + "External id": 227860,"Sequence number": 2757879, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1], [], [4194304, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 1024], [1024], [], [16, 4096, 1024], [], [], [], []], "Ev Idx": 6659 + } + }, + { + "ph": "s", "id": 77, "pid": 4183440, "tid": 4183440, "ts": 667115411306.600, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115411322.748, "dur": 2.909, + "args": { + "External id": 227861,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115411323.794, "dur": 1.763, + "args": { + "External id": 227862,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 4183440, "tid": 4183440, + "ts": 667115411329.426, "dur": 3.329, + "args": { + "External id": 227863,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1024, 1]], "Input Dims": [[16, 4096, 1024], [65536, 1024]], "Ev Idx": 6662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115411330.792, "dur": 1.859, + "args": { + "External id": 227864,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115411331.527, "dur": 1.032, + "args": { + "External id": 227865,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115411340.088, "dur": 6.537, + "args": { + "External id": 227866,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 6665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115411342.249, "dur": 4.089, + "args": { + "External id": 227867,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115411352.825, "dur": 3.386, + "args": { + "External id": 227868,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115411359.614, "dur": 3.264, + "args": { + "External id": 227869,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115411478.834, "dur": 2.865, + "args": { + "External id": 227870,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115411479.712, "dur": 1.762, + "args": { + "External id": 227871,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115411484.105, "dur": 2.502, + "args": { + "External id": 227872,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115411485.436, "dur": 1.078, + "args": { + "External id": 227873,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115411539.166, "dur": 97.377, + "args": { + "External id": 227874,"Sequence number": 2757880, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [2816, 1024], []], "Ev Idx": 6673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115411540.058, "dur": 9.390, + "args": { + "External id": 227875,"Sequence number": 2757880, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 6674 + } + }, + { + "ph": "s", "id": 76, "pid": 4183440, "tid": 4183440, "ts": 667115411540.058, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115411542.870, "dur": 5.132, + "args": { + "External id": 227876,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 6675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115411546.167, "dur": 1.543, + "args": { + "External id": 227877,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 6676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115411550.497, "dur": 85.762, + "args": { + "External id": 227878,"Sequence number": 2757881, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 2816]], "Ev Idx": 6677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115411552.100, "dur": 4.058, + "args": { + "External id": 227879,"Sequence number": 2757881, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115411553.363, "dur": 2.654, + "args": { + "External id": 227880,"Sequence number": 2757881, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6679 + } + }, + { + "ph": "s", "id": 75, "pid": 4183440, "tid": 4183440, "ts": 667115411553.363, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115411557.381, "dur": 71.584, + "args": { + "External id": 227881,"Sequence number": 2757882, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 2816]], "Ev Idx": 6680 + } + }, + { + "ph": "s", "id": 74, "pid": 4183440, "tid": 4183440, "ts": 667115411557.381, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115411631.138, "dur": 4.586, + "args": { + "External id": 227882,"Sequence number": 2757883, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1], []], "Input Dims": [[65536, 2816], []], "Ev Idx": 6681 + } + }, + { + "ph": "s", "id": 73, "pid": 4183440, "tid": 4183440, "ts": 667115411631.138, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115411644.064, "dur": 110.756, + "args": { + "External id": 227883,"Sequence number": 2757884, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [2816, 1024], []], "Ev Idx": 6682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115411645.037, "dur": 6.256, + "args": { + "External id": 227884,"Sequence number": 2757884, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 6683 + } + }, + { + "ph": "s", "id": 72, "pid": 4183440, "tid": 4183440, "ts": 667115411645.037, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115411646.869, "dur": 3.437, + "args": { + "External id": 227885,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 6684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115411649.048, "dur": 1.108, + "args": { + "External id": 227886,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 6685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115411652.293, "dur": 102.228, + "args": { + "External id": 227887,"Sequence number": 2757885, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 2816]], "Ev Idx": 6686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115411653.517, "dur": 44.716, + "args": { + "External id": 227888,"Sequence number": 2757885, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115411689.677, "dur": 8.192, + "args": { + "External id": 227889,"Sequence number": 2757885, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6688 + } + }, + { + "ph": "s", "id": 71, "pid": 4183440, "tid": 4183440, "ts": 667115411689.677, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115411699.488, "dur": 47.935, + "args": { + "External id": 227890,"Sequence number": 2757886, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 2816]], "Ev Idx": 6689 + } + }, + { + "ph": "s", "id": 70, "pid": 4183440, "tid": 4183440, "ts": 667115411699.488, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115411749.150, "dur": 4.780, + "args": { + "External id": 227891,"Sequence number": 2757887, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1], []], "Input Dims": [[65536, 2816], []], "Ev Idx": 6690 + } + }, + { + "ph": "s", "id": 69, "pid": 4183440, "tid": 4183440, "ts": 667115411749.150, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115411779.862, "dur": 145.903, + "args": { + "External id": 227892,"Sequence number": 2757888, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[11534336, 2816, 1], [11534336, 2816, 1], [2816, 1], []], "Input Dims": [[16, 4096, 2816], [16, 4096, 2816], [1024, 2816], []], "Ev Idx": 6691 + } + }, + { + "ph": "s", "id": 68, "pid": 4183440, "tid": 4183440, "ts": 667115411779.862, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115411820.215, "dur": 4.597, + "args": { + "External id": 227893,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2816]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115411855.001, "dur": 56.500, + "args": { + "External id": 227894,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[11534336, 2816, 1], [2816, 1], []], "Input Dims": [[16, 4096, 2816], [1024, 2816], []], "Ev Idx": 6693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115411855.936, "dur": 5.537, + "args": { + "External id": 227895,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 6694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115411857.210, "dur": 3.348, + "args": { + "External id": 227896,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2816, 1], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 6695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115411859.431, "dur": 0.967, + "args": { + "External id": 227897,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 6696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115411862.160, "dur": 48.956, + "args": { + "External id": 227898,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[11534336, 2816, 1], [1, 2816]], "Input Dims": [[16, 4096, 2816], [2816, 1024]], "Ev Idx": 6697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115411864.177, "dur": 2.670, + "args": { + "External id": 227899,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 6698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115411865.175, "dur": 1.547, + "args": { + "External id": 227900,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 6699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115411867.837, "dur": 39.582, + "args": { + "External id": 227901,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816]], "Input Dims": [[65536, 2816], [2816, 1024]], "Ev Idx": 6700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115411909.160, "dur": 1.291, + "args": { + "External id": 227902,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 4183440, "tid": 4183440, + "ts": 667115411935.036, "dur": 24.538, + "args": { + "External id": 227903,"Sequence number": 2757889, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 6702 + } + }, + { + "ph": "s", "id": 67, "pid": 4183440, "tid": 4183440, "ts": 667115411935.036, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115411994.846, "dur": 189.175, + "args": { + "External id": 227904,"Sequence number": 2757890, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1], [], [], [], [], [], []], "Input Dims": [[16, 4096, 1024], [1024], [], [], [], [], [], []], "Ev Idx": 6703 + } + }, + { + "ph": "s", "id": 66, "pid": 4183440, "tid": 4183440, "ts": 667115411994.846, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115412013.116, "dur": 3.546, + "args": { + "External id": 227905,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115412014.487, "dur": 1.813, + "args": { + "External id": 227906,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115412024.935, "dur": 7.817, + "args": { + "External id": 227907,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 6706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115412027.877, "dur": 4.425, + "args": { + "External id": 227908,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115412038.997, "dur": 3.460, + "args": { + "External id": 227909,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115412168.802, "dur": 3.091, + "args": { + "External id": 227910,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115412169.766, "dur": 1.753, + "args": { + "External id": 227911,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115412202.288, "dur": 78.962, + "args": { + "External id": 227912,"Sequence number": 2757891, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [1024, 1024], []], "Ev Idx": 6711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115412203.507, "dur": 7.615, + "args": { + "External id": 227913,"Sequence number": 2757891, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 6712 + } + }, + { + "ph": "s", "id": 65, "pid": 4183440, "tid": 4183440, "ts": 667115412203.507, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115412206.000, "dur": 3.813, + "args": { + "External id": 227914,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 6713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115412208.323, "dur": 1.302, + "args": { + "External id": 227915,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 6714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115412211.818, "dur": 69.218, + "args": { + "External id": 227916,"Sequence number": 2757892, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 1024]], "Ev Idx": 6715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115412213.891, "dur": 5.052, + "args": { + "External id": 227917,"Sequence number": 2757892, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115412215.268, "dur": 3.546, + "args": { + "External id": 227918,"Sequence number": 2757892, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6717 + } + }, + { + "ph": "s", "id": 64, "pid": 4183440, "tid": 4183440, "ts": 667115412215.268, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115412219.712, "dur": 55.061, + "args": { + "External id": 227919,"Sequence number": 2757893, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 6718 + } + }, + { + "ph": "s", "id": 63, "pid": 4183440, "tid": 4183440, "ts": 667115412219.712, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115412277.102, "dur": 3.319, + "args": { + "External id": 227920,"Sequence number": 2757894, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6719 + } + }, + { + "ph": "s", "id": 62, "pid": 4183440, "tid": 4183440, "ts": 667115412277.102, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115412288.585, "dur": 60.021, + "args": { + "External id": 227921,"Sequence number": 2757895, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [1024, 1024], []], "Ev Idx": 6720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115412289.395, "dur": 6.354, + "args": { + "External id": 227922,"Sequence number": 2757895, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 6721 + } + }, + { + "ph": "s", "id": 61, "pid": 4183440, "tid": 4183440, "ts": 667115412289.395, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115412291.340, "dur": 3.178, + "args": { + "External id": 227923,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 6722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115412293.393, "dur": 0.948, + "args": { + "External id": 227924,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 6723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115412296.555, "dur": 51.837, + "args": { + "External id": 227925,"Sequence number": 2757896, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 1024]], "Ev Idx": 6724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115412297.928, "dur": 4.275, + "args": { + "External id": 227926,"Sequence number": 2757896, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115412299.640, "dur": 2.435, + "args": { + "External id": 227927,"Sequence number": 2757896, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6726 + } + }, + { + "ph": "s", "id": 60, "pid": 4183440, "tid": 4183440, "ts": 667115412299.640, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115412303.309, "dur": 38.770, + "args": { + "External id": 227928,"Sequence number": 2757897, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 6727 + } + }, + { + "ph": "s", "id": 59, "pid": 4183440, "tid": 4183440, "ts": 667115412303.309, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115412343.689, "dur": 4.276, + "args": { + "External id": 227929,"Sequence number": 2757898, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6728 + } + }, + { + "ph": "s", "id": 58, "pid": 4183440, "tid": 4183440, "ts": 667115412343.689, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115412355.867, "dur": 62.019, + "args": { + "External id": 227930,"Sequence number": 2757899, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [1024, 1024], []], "Ev Idx": 6729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115412356.605, "dur": 8.832, + "args": { + "External id": 227931,"Sequence number": 2757899, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 6730 + } + }, + { + "ph": "s", "id": 57, "pid": 4183440, "tid": 4183440, "ts": 667115412356.605, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115412359.326, "dur": 4.756, + "args": { + "External id": 227932,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 6731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115412360.972, "dur": 2.743, + "args": { + "External id": 227933,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 6732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115412366.601, "dur": 51.029, + "args": { + "External id": 227934,"Sequence number": 2757900, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 1024]], "Ev Idx": 6733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115412367.838, "dur": 4.531, + "args": { + "External id": 227935,"Sequence number": 2757900, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115412368.967, "dur": 3.177, + "args": { + "External id": 227936,"Sequence number": 2757900, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6735 + } + }, + { + "ph": "s", "id": 56, "pid": 4183440, "tid": 4183440, "ts": 667115412368.967, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115412373.093, "dur": 38.066, + "args": { + "External id": 227937,"Sequence number": 2757901, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 6736 + } + }, + { + "ph": "s", "id": 55, "pid": 4183440, "tid": 4183440, "ts": 667115412373.093, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115412412.675, "dur": 4.564, + "args": { + "External id": 227938,"Sequence number": 2757902, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6737 + } + }, + { + "ph": "s", "id": 54, "pid": 4183440, "tid": 4183440, "ts": 667115412412.675, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115412431.913, "dur": 4.965, + "args": { + "External id": 227939,"Sequence number": 2757903, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115412433.148, "dur": 3.265, + "args": { + "External id": 227940,"Sequence number": 2757903, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6739 + } + }, + { + "ph": "s", "id": 53, "pid": 4183440, "tid": 4183440, "ts": 667115412433.148, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115412443.097, "dur": 3.049, + "args": { + "External id": 227941,"Sequence number": 2757904, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115412444.312, "dur": 1.710, + "args": { + "External id": 227942,"Sequence number": 2757904, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6741 + } + }, + { + "ph": "s", "id": 52, "pid": 4183440, "tid": 4183440, "ts": 667115412444.312, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115412450.335, "dur": 3.404, + "args": { + "External id": 227943,"Sequence number": 2757905, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115412451.390, "dur": 2.218, + "args": { + "External id": 227944,"Sequence number": 2757905, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 16, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6743 + } + }, + { + "ph": "s", "id": 51, "pid": 4183440, "tid": 4183440, "ts": 667115412451.390, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115412481.861, "dur": 213.326, + "args": { + "External id": 227945,"Sequence number": 2757906, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 6744 + } + }, + { + "ph": "s", "id": 50, "pid": 4183440, "tid": 4183440, "ts": 667115412481.861, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115412519.710, "dur": 11.134, + "args": { + "External id": 227946,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 6745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115412522.390, "dur": 7.925, + "args": { + "External id": 227947,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115412719.476, "dur": 117.014, + "args": { + "External id": 227948,"Sequence number": 2757907, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 6747 + } + }, + { + "ph": "s", "id": 49, "pid": 4183440, "tid": 4183440, "ts": 667115412719.476, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115412735.225, "dur": 9.282, + "args": { + "External id": 227949,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 6748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115412737.900, "dur": 6.127, + "args": { + "External id": 227950,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 4183440, "tid": 4183440, + "ts": 667115412864.191, "dur": 177.667, + "args": { + "External id": 227951,"Sequence number": 2757908, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], [], []], "Ev Idx": 6750 + } + }, + { + "ph": "s", "id": 48, "pid": 4183440, "tid": 4183440, "ts": 667115412864.191, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115412892.386, "dur": 124.275, + "args": { + "External id": 227952,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [4194304, 1024, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [16, 4096, 16, 64], [16, 4096, 16, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115412942.534, "dur": 7.260, + "args": { + "External id": 227953,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[4194304, 1024, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 16, 64], [], [], [], [], []], "Ev Idx": 6752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115412944.766, "dur": 4.514, + "args": { + "External id": 227954,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 16, 64]", "[4194304, 1024, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115412952.461, "dur": 4.789, + "args": { + "External id": 227955,"Record function id": 0, "Concrete Inputs": ["[16, 16, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115412958.692, "dur": 1.938, + "args": { + "External id": 227956,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115412963.124, "dur": 5.166, + "args": { + "External id": 227957,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 4183440, "tid": 4183440, + "ts": 667115413027.506, "dur": 4.832, + "args": { + "External id": 227958,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 64, 1]], "Input Dims": [[16, 4096, 16, 64]], "Ev Idx": 6757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115413046.791, "dur": 6.378, + "args": { + "External id": 227959,"Sequence number": 2757909, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 6758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115413048.713, "dur": 4.327, + "args": { + "External id": 227960,"Sequence number": 2757909, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 64, 1], []], "Input Dims": [[16, 4096, 16, 64], []], "Ev Idx": 6759 + } + }, + { + "ph": "s", "id": 47, "pid": 4183440, "tid": 4183440, "ts": 667115413048.713, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115413065.693, "dur": 99.134, + "args": { + "External id": 227961,"Sequence number": 2757910, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [1024, 1024], []], "Ev Idx": 6760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115413067.247, "dur": 8.524, + "args": { + "External id": 227962,"Sequence number": 2757910, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[1024, 1024]], "Ev Idx": 6761 + } + }, + { + "ph": "s", "id": 46, "pid": 4183440, "tid": 4183440, "ts": 667115413067.247, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115413070.068, "dur": 4.654, + "args": { + "External id": 227963,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[1024, 1024], [], []], "Ev Idx": 6762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115413073.069, "dur": 1.428, + "args": { + "External id": 227964,"Record function id": 0, "Concrete Inputs": ["", "[1024, 1024]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[1024, 1024], [], [], []], "Ev Idx": 6763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115413077.158, "dur": 87.365, + "args": { + "External id": 227965,"Sequence number": 2757911, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 1024]], "Ev Idx": 6764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115413079.091, "dur": 3.604, + "args": { + "External id": 227966,"Sequence number": 2757911, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115413080.229, "dur": 2.290, + "args": { + "External id": 227967,"Sequence number": 2757911, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6766 + } + }, + { + "ph": "s", "id": 45, "pid": 4183440, "tid": 4183440, "ts": 667115413080.229, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115413084.149, "dur": 73.681, + "args": { + "External id": 227968,"Sequence number": 2757912, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 1024]], "Ev Idx": 6767 + } + }, + { + "ph": "s", "id": 44, "pid": 4183440, "tid": 4183440, "ts": 667115413084.149, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115413159.945, "dur": 3.900, + "args": { + "External id": 227969,"Sequence number": 2757913, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6768 + } + }, + { + "ph": "s", "id": 43, "pid": 4183440, "tid": 4183440, "ts": 667115413159.945, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115413195.806, "dur": 192.558, + "args": { + "External id": 227970,"Sequence number": 2757914, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 1], [1], [], [4194304, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 1024], [1024], [], [16, 4096, 1024], [], [], [], []], "Ev Idx": 6769 + } + }, + { + "ph": "s", "id": 42, "pid": 4183440, "tid": 4183440, "ts": 667115413195.806, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115413212.526, "dur": 3.035, + "args": { + "External id": 227971,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115413213.949, "dur": 1.488, + "args": { + "External id": 227972,"Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 4183440, "tid": 4183440, + "ts": 667115413219.451, "dur": 4.000, + "args": { + "External id": 227973,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1024, 1]], "Input Dims": [[16, 4096, 1024], [65536, 1024]], "Ev Idx": 6772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115413221.032, "dur": 2.309, + "args": { + "External id": 227974,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115413222.150, "dur": 1.095, + "args": { + "External id": 227975,"Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115413230.677, "dur": 6.570, + "args": { + "External id": 227976,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 6775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115413232.734, "dur": 4.093, + "args": { + "External id": 227977,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115413243.321, "dur": 3.257, + "args": { + "External id": 227978,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115413250.177, "dur": 3.329, + "args": { + "External id": 227979,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115413367.492, "dur": 5.202, + "args": { + "External id": 227980,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115413368.552, "dur": 3.916, + "args": { + "External id": 227981,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115413375.618, "dur": 2.693, + "args": { + "External id": 227982,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115413377.015, "dur": 1.190, + "args": { + "External id": 227983,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115413405.384, "dur": 78.282, + "args": { + "External id": 227984,"Sequence number": 2757915, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [2816, 1024], []], "Ev Idx": 6783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115413406.272, "dur": 6.927, + "args": { + "External id": 227985,"Sequence number": 2757915, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 6784 + } + }, + { + "ph": "s", "id": 41, "pid": 4183440, "tid": 4183440, "ts": 667115413406.272, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115413408.297, "dur": 3.863, + "args": { + "External id": 227986,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 6785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115413410.809, "dur": 1.112, + "args": { + "External id": 227987,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 6786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115413414.103, "dur": 69.347, + "args": { + "External id": 227988,"Sequence number": 2757916, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 2816]], "Ev Idx": 6787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115413415.784, "dur": 5.686, + "args": { + "External id": 227989,"Sequence number": 2757916, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115413416.862, "dur": 4.373, + "args": { + "External id": 227990,"Sequence number": 2757916, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6789 + } + }, + { + "ph": "s", "id": 40, "pid": 4183440, "tid": 4183440, "ts": 667115413416.862, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115413422.342, "dur": 55.161, + "args": { + "External id": 227991,"Sequence number": 2757917, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 2816]], "Ev Idx": 6790 + } + }, + { + "ph": "s", "id": 39, "pid": 4183440, "tid": 4183440, "ts": 667115413422.342, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115413479.526, "dur": 3.426, + "args": { + "External id": 227992,"Sequence number": 2757918, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1], []], "Input Dims": [[65536, 2816], []], "Ev Idx": 6791 + } + }, + { + "ph": "s", "id": 38, "pid": 4183440, "tid": 4183440, "ts": 667115413479.526, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115413512.078, "dur": 79.463, + "args": { + "External id": 227993,"Sequence number": 2757919, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 1], [1024, 1], []], "Input Dims": [[16, 4096, 1024], [2816, 1024], []], "Ev Idx": 6792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115413513.076, "dur": 12.819, + "args": { + "External id": 227994,"Sequence number": 2757919, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[2816, 1024]], "Ev Idx": 6793 + } + }, + { + "ph": "s", "id": 37, "pid": 4183440, "tid": 4183440, "ts": 667115413513.076, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115413518.487, "dur": 5.939, + "args": { + "External id": 227995,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[2816, 1024], [], []], "Ev Idx": 6794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115413522.893, "dur": 1.199, + "args": { + "External id": 227996,"Record function id": 0, "Concrete Inputs": ["", "[1024, 2816]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[2816, 1024], [], [], []], "Ev Idx": 6795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115413527.139, "dur": 64.168, + "args": { + "External id": 227997,"Sequence number": 2757920, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4194304, 1024, 1], [1, 1024]], "Input Dims": [[16, 4096, 1024], [1024, 2816]], "Ev Idx": 6796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115413528.831, "dur": 5.531, + "args": { + "External id": 227998,"Sequence number": 2757920, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115413530.112, "dur": 4.109, + "args": { + "External id": 227999,"Sequence number": 2757920, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6798 + } + }, + { + "ph": "s", "id": 36, "pid": 4183440, "tid": 4183440, "ts": 667115413530.112, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115413535.296, "dur": 48.903, + "args": { + "External id": 228000,"Sequence number": 2757921, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[65536, 1024], [1024, 2816]], "Ev Idx": 6799 + } + }, + { + "ph": "s", "id": 35, "pid": 4183440, "tid": 4183440, "ts": 667115413535.296, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115413586.023, "dur": 4.821, + "args": { + "External id": 228001,"Sequence number": 2757922, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2816, 1], []], "Input Dims": [[65536, 2816], []], "Ev Idx": 6800 + } + }, + { + "ph": "s", "id": 34, "pid": 4183440, "tid": 4183440, "ts": 667115413586.023, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115413613.272, "dur": 188.610, + "args": { + "External id": 228002,"Sequence number": 2757923, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[11534336, 2816, 1], [11534336, 2816, 1], [2816, 1], []], "Input Dims": [[16, 4096, 2816], [16, 4096, 2816], [1024, 2816], []], "Ev Idx": 6801 + } + }, + { + "ph": "s", "id": 33, "pid": 4183440, "tid": 4183440, "ts": 667115413613.272, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115413649.837, "dur": 4.002, + "args": { + "External id": 228003,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2816]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115413723.412, "dur": 63.473, + "args": { + "External id": 228004,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[11534336, 2816, 1], [2816, 1], []], "Input Dims": [[16, 4096, 2816], [1024, 2816], []], "Ev Idx": 6803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115413724.678, "dur": 6.196, + "args": { + "External id": 228005,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2816, 1]], "Input Dims": [[1024, 2816]], "Ev Idx": 6804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115413726.116, "dur": 3.737, + "args": { + "External id": 228006,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2816, 1], [], []], "Input Dims": [[1024, 2816], [], []], "Ev Idx": 6805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115413728.519, "dur": 1.058, + "args": { + "External id": 228007,"Record function id": 0, "Concrete Inputs": ["", "[2816, 1024]", "[1, 2816]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2816, 1], [], [], []], "Input Dims": [[1024, 2816], [], [], []], "Ev Idx": 6806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115413731.709, "dur": 54.911, + "args": { + "External id": 228008,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[11534336, 2816, 1], [1, 2816]], "Input Dims": [[16, 4096, 2816], [2816, 1024]], "Ev Idx": 6807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 4183440, "tid": 4183440, + "ts": 667115413733.373, "dur": 2.932, + "args": { + "External id": 228009,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 6808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115413734.432, "dur": 1.722, + "args": { + "External id": 228010,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2816]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 2816, 1], []], "Input Dims": [[16, 4096, 2816], []], "Ev Idx": 6809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115413737.271, "dur": 44.917, + "args": { + "External id": 228011,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2816, 1], [1, 2816]], "Input Dims": [[65536, 2816], [2816, 1024]], "Ev Idx": 6810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 4183440, "tid": 4183440, + "ts": 667115413784.499, "dur": 1.406, + "args": { + "External id": 228012,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 4183440, "tid": 4183440, + "ts": 667115413811.611, "dur": 24.824, + "args": { + "External id": 228013,"Sequence number": 2757924, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 1], [4194304, 1024, 1], []], "Input Dims": [[16, 4096, 1024], [16, 4096, 1024], []], "Ev Idx": 6812 + } + }, + { + "ph": "s", "id": 32, "pid": 4183440, "tid": 4183440, "ts": 667115413811.611, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 4183440, "tid": 4183440, + "ts": 667115413855.422, "dur": 41.690, + "args": { + "External id": 228014,"Sequence number": 2757925, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "-2"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[[4194304, 1024, 1], [4194304, 1024, 1], [4194304, 1024, 1], [4194304, 1024, 1]], []], "Input Dims": [[[16, 4096, 1024], [16, 4096, 1024], [16, 4096, 1024], [16, 4096, 1024]], []], "Ev Idx": 6813 + } + }, + { + "ph": "s", "id": 31, "pid": 4183440, "tid": 4183440, "ts": 667115413855.422, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 4183440, "tid": 4183440, + "ts": 667115413863.569, "dur": 29.018, + "args": { + "External id": 228015,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[[4194304, 1024, 1], [4194304, 1024, 1], [4194304, 1024, 1], [4194304, 1024, 1]], []], "Input Dims": [[[16, 4096, 1024], [16, 4096, 1024], [16, 4096, 1024], [16, 4096, 1024]], []], "Ev Idx": 6814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115413894.130, "dur": 1.564, + "args": { + "External id": 228016,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[16, 4096, 4096], []], "Ev Idx": 6815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 4183440, "tid": 4183440, + "ts": 667115413937.587, "dur": 48.014, + "args": { + "External id": 228017,"Record function id": 0, "Ev Idx": 6816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 2/0", "pid": 4183440, "tid": 4183440, + "ts": 667115413986.783, "dur": 187.730, + "args": { + "External id": 228018,"Record function id": 0, "Ev Idx": 6817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115414025.514, "dur": 140.443, + "args": { + "External id": 228019,"Sequence number": 2757926, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1], [16777216, 4096, 1024, 1]], "Input Dims": [[1024], [16, 4096, 4, 1024]], "Ev Idx": 6818 + } + }, + { + "ph": "s", "id": 30, "pid": 4183440, "tid": 4183440, "ts": 667115414025.514, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 4183440, "tid": 4183440, + "ts": 667115414091.357, "dur": 36.813, + "args": { + "External id": 228020,"kernel_hash": "ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "1024", "1", "9.9999999999999995e-07", "True", "1024", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/k4/ck4apib4lp3ng7t5dwwm5qlikeosbnhrlf2sblbxilqmogtmpafh.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[262144, 1024], [262144, 1024], [1024], [262144], [], [], [], [], [], [], [], [], []], "Ev Idx": 6819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 4183440, + "ts": 667115414252.867, "dur": 36.960, + "args": { + "External id": 228021,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 6820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115414256.316, "dur": 5.078, + "args": { + "External id": 228022,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 4183440, + "ts": 667115414264.406, "dur": 25.124, + "args": { + "External id": 228023,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 6822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115414267.855, "dur": 20.939, + "args": { + "External id": 228024,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 6823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 4183440, + "ts": 667115414293.508, "dur": 18.705, + "args": { + "External id": 228025,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 6824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115414295.090, "dur": 2.658, + "args": { + "External id": 228026,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 4183440, + "ts": 667115414298.901, "dur": 13.051, + "args": { + "External id": 228027,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 6826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115414299.448, "dur": 12.060, + "args": { + "External id": 228028,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 6827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 4183440, + "ts": 667115414315.227, "dur": 16.301, + "args": { + "External id": 228029,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 6828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115414316.730, "dur": 2.797, + "args": { + "External id": 228030,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 4183440, + "ts": 667115414320.488, "dur": 10.786, + "args": { + "External id": 228031,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 6830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115414321.162, "dur": 9.750, + "args": { + "External id": 228032,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 6831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115414341.393, "dur": 0.866, + "args": { + "External id": 228033,"Sequence number": 2757927, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], [], []], "Input Dims": [[16, 8192], [], [], [], [], [], [], []], "Ev Idx": 6832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 4183440, "tid": 4183440, + "ts": 667115414350.518, "dur": 8.577, + "args": { + "External id": 228034,"Sequence number": 2757927, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "5", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 8192], [], [], []], "Ev Idx": 6833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414356.050, "dur": 1.593, + "args": { + "External id": 228035,"Record function id": 0, "Concrete Inputs": ["", "[16, 8188, 5]", "[8192, 1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 8192], [], [], []], "Ev Idx": 6834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115414365.507, "dur": 6.755, + "args": { + "External id": 228036,"Sequence number": 2757927, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 8188, 5], [], [], [], []], "Ev Idx": 6835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414369.638, "dur": 0.905, + "args": { + "External id": 228037,"Record function id": 0, "Concrete Inputs": ["", "[16, 8188, 5]", "[8192, 1, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 8188, 5], [], [], []], "Ev Idx": 6836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115414373.521, "dur": 4.001, + "args": { + "External id": 228038,"Sequence number": 2757927, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 8188, 5], [], [], [], []], "Ev Idx": 6837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414375.953, "dur": 0.849, + "args": { + "External id": 228039,"Record function id": 0, "Concrete Inputs": ["", "[16, 8188, 5]", "[8192, 1, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 8188, 5], [], [], []], "Ev Idx": 6838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115414378.846, "dur": 3.082, + "args": { + "External id": 228040,"Sequence number": 2757927, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "1", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 8188, 5], [], [], [], []], "Ev Idx": 6839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414380.626, "dur": 0.779, + "args": { + "External id": 228041,"Record function id": 0, "Concrete Inputs": ["", "[16, 8188, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 8188, 5], [], [], []], "Ev Idx": 6840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115414385.082, "dur": 2.964, + "args": { + "External id": 228042,"Sequence number": 2757927, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 8188, 4], [], [], [], []], "Ev Idx": 6841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414386.999, "dur": 0.513, + "args": { + "External id": 228043,"Record function id": 0, "Concrete Inputs": ["", "[16, 8188, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 8188, 4], [], [], []], "Ev Idx": 6842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115414389.132, "dur": 3.348, + "args": { + "External id": 228044,"Sequence number": 2757927, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 8188, 4], [], [], [], []], "Ev Idx": 6843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414390.971, "dur": 0.816, + "args": { + "External id": 228045,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 8188, 4], [], [], []], "Ev Idx": 6844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115414393.610, "dur": 3.251, + "args": { + "External id": 228046,"Sequence number": 2757927, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 4096, 4], [], [], [], []], "Ev Idx": 6845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414395.650, "dur": 0.699, + "args": { + "External id": 228047,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4096, 4], [], [], []], "Ev Idx": 6846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115414400.222, "dur": 5.527, + "args": { + "External id": 228048,"Sequence number": 2757927, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "2"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[16, 4096, 4], [], []], "Ev Idx": 6847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414404.093, "dur": 0.965, + "args": { + "External id": 228049,"Record function id": 0, "Concrete Inputs": ["", "[16, 4, 4096]", "[8192, 1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4096, 4], [], [], []], "Ev Idx": 6848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115414409.750, "dur": 3.412, + "args": { + "External id": 228050,"Sequence number": 2757927, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 4, 4096], [], [], [], []], "Ev Idx": 6849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414412.023, "dur": 0.553, + "args": { + "External id": 228051,"Record function id": 0, "Concrete Inputs": ["", "[16, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 6850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183440, "tid": 4183440, + "ts": 667115414416.998, "dur": 7.654, + "args": { + "External id": 228052,"Sequence number": 2757927, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[16, 4, 4096], [], []], "Ev Idx": 6851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414422.818, "dur": 0.791, + "args": { + "External id": 228053,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 6852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115414426.040, "dur": 2.967, + "args": { + "External id": 228054,"Sequence number": 2757927, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], []], "Ev Idx": 6853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414427.689, "dur": 0.780, + "args": { + "External id": 228055,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 6854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115414431.327, "dur": 5.913, + "args": { + "External id": 228056,"Sequence number": 2757927, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], []], "Ev Idx": 6855 + } + }, + { + "ph": "s", "id": 29, "pid": 4183440, "tid": 4183440, "ts": 667115414431.327, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414435.296, "dur": 0.592, + "args": { + "External id": 228057,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "[16777216, 4096, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 6856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115414438.186, "dur": 5.669, + "args": { + "External id": 228058,"Sequence number": 2757928, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], []], "Ev Idx": 6857 + } + }, + { + "ph": "s", "id": 28, "pid": 4183440, "tid": 4183440, "ts": 667115414438.186, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414442.322, "dur": 0.805, + "args": { + "External id": 228059,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "[16777216, 4096, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 6858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183440, "tid": 4183440, + "ts": 667115414444.767, "dur": 6.089, + "args": { + "External id": 228060,"Sequence number": 2757929, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], []], "Input Dims": [[16, 4096, 4, 1024], [], []], "Ev Idx": 6859 + } + }, + { + "ph": "s", "id": 27, "pid": 4183440, "tid": 4183440, "ts": 667115414444.767, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414449.147, "dur": 0.875, + "args": { + "External id": 228061,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 6860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115414451.938, "dur": 4.953, + "args": { + "External id": 228062,"Sequence number": 2757930, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], [], []], "Ev Idx": 6861 + } + }, + { + "ph": "s", "id": 26, "pid": 4183440, "tid": 4183440, "ts": 667115414451.938, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414455.109, "dur": 1.050, + "args": { + "External id": 228063,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], []], "Ev Idx": 6862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183440, "tid": 4183440, + "ts": 667115414460.957, "dur": 62.381, + "args": { + "External id": 228064,"Sequence number": 2757931, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 6863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 4183440, + "ts": 667115414463.317, "dur": 59.682, + "args": { + "External id": 228065,"Sequence number": 2757931, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 6864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115414465.702, "dur": 8.858, + "args": { + "External id": 228066,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], []], "Ev Idx": 6865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115414468.281, "dur": 5.691, + "args": { + "External id": 228067,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115414475.993, "dur": 46.261, + "args": { + "External id": 228068,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 6867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115414552.022, "dur": 6.458, + "args": { + "External id": 228069,"Sequence number": 2757931, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 6868 + } + }, + { + "ph": "s", "id": 25, "pid": 4183440, "tid": 4183440, "ts": 667115414552.022, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115414561.097, "dur": 1.919, + "args": { + "External id": 228070,"Sequence number": 2757932, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 6869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115414589.028, "dur": 21489.187, + "args": { + "External id": 228071,"Sequence number": 2757932, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536], [32000, 1024], [], [], [], [], []], "Ev Idx": 6870 + } + }, + { + "ph": "s", "id": 24, "pid": 4183440, "tid": 4183440, "ts": 667115414589.028, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183440, "tid": 4183440, + "ts": 667115414603.047, "dur": 31.678, + "args": { + "External id": 228072,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 4183440, + "ts": 667115414604.177, "dur": 30.300, + "args": { + "External id": 228073,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115414606.029, "dur": 7.135, + "args": { + "External id": 228074,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 6873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115414608.076, "dur": 4.670, + "args": { + "External id": 228075,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115414614.154, "dur": 19.885, + "args": { + "External id": 228076,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [4096, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 6875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 4183440, "tid": 4183440, + "ts": 667115414651.455, "dur": 77.455, + "args": { + "External id": 228077,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 6876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115414697.449, "dur": 9.756, + "args": { + "External id": 228078,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 6877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414700.935, "dur": 5.800, + "args": { + "External id": 228079,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 4183440, + "ts": 667115414708.285, "dur": 20.419, + "args": { + "External id": 228080,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 6879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115414709.641, "dur": 18.627, + "args": { + "External id": 228081,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 6880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 4183440, "tid": 4183440, + "ts": 667115414733.605, "dur": 20.753, + "args": { + "External id": 228082,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[32000, 1024], [], [], [], [], []], "Ev Idx": 6881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115414734.492, "dur": 5.404, + "args": { + "External id": 228083,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[32000, 1024], [], [], [], [], []], "Ev Idx": 6882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414736.378, "dur": 3.234, + "args": { + "External id": 228084,"Record function id": 0, "Concrete Inputs": ["[32000, 1024]", "[1024, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 4183440, + "ts": 667115414740.661, "dur": 13.475, + "args": { + "External id": 228085,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 6884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115414741.333, "dur": 12.425, + "args": { + "External id": 228086,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1024, 1], []], "Input Dims": [[32000, 1024], []], "Ev Idx": 6885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 4183440, + "ts": 667115414759.273, "dur": 16.892, + "args": { + "External id": 228087,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 6886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115414760.486, "dur": 3.582, + "args": { + "External id": 228088,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 4183440, + "ts": 667115414764.890, "dur": 10.997, + "args": { + "External id": 228089,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[65536]], "Ev Idx": 6888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115414765.612, "dur": 9.945, + "args": { + "External id": 228090,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 6889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 4183440, "tid": 4183440, + "ts": 667115414782.797, "dur": 26.307, + "args": { + "External id": 228091,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 6890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115414813.711, "dur": 63.428, + "args": { + "External id": 228092,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 6891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115414817.887, "dur": 58.780, + "args": { + "External id": 228093,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 6892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414825.310, "dur": 1.166, + "args": { + "External id": 228094,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 6893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115414828.482, "dur": 27.197, + "args": { + "External id": 228095,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 6894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115414833.065, "dur": 22.422, + "args": { + "External id": 228096,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[65536], [], [], [], [], [], []], "Ev Idx": 6895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115414835.374, "dur": 2.937, + "args": { + "External id": 228097,"Record function id": 0, "Concrete Inputs": ["[65536]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115414839.298, "dur": 15.858, + "args": { + "External id": 228098,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[65536], [65536], []], "Ev Idx": 6897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 4183440, "tid": 4183440, + "ts": 667115414882.315, "dur": 15356.550, + "args": { + "External id": 228099,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 6898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 4183440, "tid": 4183440, + "ts": 667115414884.549, "dur": 15353.234, + "args": { + "External id": 228100,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 6899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115430249.461, "dur": 7.123, + "args": { + "External id": 228101,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 6900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115430253.755, "dur": 1.233, + "args": { + "External id": 228102,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 6901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115430262.617, "dur": 113.132, + "args": { + "External id": 228103,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 6902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115430264.354, "dur": 7.480, + "args": { + "External id": 228104,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 6903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115430266.822, "dur": 4.016, + "args": { + "External id": 228105,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 6904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115430269.347, "dur": 1.269, + "args": { + "External id": 228106,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 6905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115430273.550, "dur": 101.492, + "args": { + "External id": 228107,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 6906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115430275.548, "dur": 98.564, + "args": { + "External id": 228108,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 6907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115430379.838, "dur": 4.853, + "args": { + "External id": 228109,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 6908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115430382.529, "dur": 0.665, + "args": { + "External id": 228110,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 6909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115430393.353, "dur": 4.118, + "args": { + "External id": 228111,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 6910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115430407.530, "dur": 7.383, + "args": { + "External id": 228112,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 6911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115430410.358, "dur": 4.264, + "args": { + "External id": 228113,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115430574.289, "dur": 277.808, + "args": { + "External id": 228114,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 6913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115430577.678, "dur": 5.183, + "args": { + "External id": 228115,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115430586.035, "dur": 265.544, + "args": { + "External id": 228116,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 6915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115430589.254, "dur": 0.794, + "args": { + "External id": 228117,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 6916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115430593.125, "dur": 30.609, + "args": { + "External id": 228118,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 6917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115430626.492, "dur": 6.247, + "args": { + "External id": 228119,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 6918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115430631.194, "dur": 1.049, + "args": { + "External id": 228120,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 6919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115430634.788, "dur": 58.177, + "args": { + "External id": 228121,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 6920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115430636.063, "dur": 1.683, + "args": { + "External id": 228122,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115430640.296, "dur": 51.928, + "args": { + "External id": 228123,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 6922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115430645.074, "dur": 3.765, + "args": { + "External id": 228124,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 6923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115430695.693, "dur": 25.700, + "args": { + "External id": 228125,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 6924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115430724.570, "dur": 18.774, + "args": { + "External id": 228126,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 6925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115430747.166, "dur": 18.252, + "args": { + "External id": 228127,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 6926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115430767.900, "dur": 16.202, + "args": { + "External id": 228128,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 6927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115430787.676, "dur": 27.716, + "args": { + "External id": 228129,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 6928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115430790.535, "dur": 1.877, + "args": { + "External id": 228130,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 6929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115430795.447, "dur": 3.285, + "args": { + "External id": 228131,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 6930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115430818.299, "dur": 17.079, + "args": { + "External id": 228132,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 6931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115430838.166, "dur": 12.317, + "args": { + "External id": 228133,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 6932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115430860.602, "dur": 2.892, + "args": { + "External id": 228134,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 6933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115430870.762, "dur": 4.712, + "args": { + "External id": 228135,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 6934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115430873.271, "dur": 1.118, + "args": { + "External id": 228136,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 6935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115430964.688, "dur": 67.366, + "args": { + "External id": 228137,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 6936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115431037.988, "dur": 5.436, + "args": { + "External id": 228138,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 6937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115431040.927, "dur": 1.135, + "args": { + "External id": 228139,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 6938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115431045.421, "dur": 29.717, + "args": { + "External id": 228140,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 6939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115431081.587, "dur": 7.549, + "args": { + "External id": 228141,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 6940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115431083.645, "dur": 4.743, + "args": { + "External id": 228142,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 6941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115431085.959, "dur": 2.129, + "args": { + "External id": 228143,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 6942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115431093.498, "dur": 55.534, + "args": { + "External id": 228144,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 6943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115431094.643, "dur": 53.687, + "args": { + "External id": 228145,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 6944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115431153.699, "dur": 18.708, + "args": { + "External id": 228146,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 6945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115431178.284, "dur": 4.384, + "args": { + "External id": 228147,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 6946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115431180.714, "dur": 0.887, + "args": { + "External id": 228148,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "8388608"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 6947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115431187.472, "dur": 61.238, + "args": { + "External id": 228149,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 6948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115431188.844, "dur": 12.241, + "args": { + "External id": 228150,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 6949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115431189.557, "dur": 10.826, + "args": { + "External id": 228151,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 6950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115431199.316, "dur": 0.871, + "args": { + "External id": 228152,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 6951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115431201.924, "dur": 46.423, + "args": { + "External id": 228153,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 6952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115431204.080, "dur": 43.672, + "args": { + "External id": 228154,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 6953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115431252.749, "dur": 4.612, + "args": { + "External id": 228155,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 6954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115431254.940, "dur": 1.251, + "args": { + "External id": 228156,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 6955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115431264.104, "dur": 1.748, + "args": { + "External id": 228157,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 6956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115431274.510, "dur": 9.304, + "args": { + "External id": 228158,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 6957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115431277.563, "dur": 5.945, + "args": { + "External id": 228159,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115431381.672, "dur": 308.978, + "args": { + "External id": 228160,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 6959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115431384.143, "dur": 2.593, + "args": { + "External id": 228161,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115431388.583, "dur": 301.521, + "args": { + "External id": 228162,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 6961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115431390.498, "dur": 0.481, + "args": { + "External id": 228163,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 6962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115431392.858, "dur": 25.333, + "args": { + "External id": 228164,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 6963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115431420.187, "dur": 3.776, + "args": { + "External id": 228165,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 6964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115431422.823, "dur": 0.927, + "args": { + "External id": 228166,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 6965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115431425.117, "dur": 33.198, + "args": { + "External id": 228167,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 6966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115431426.570, "dur": 1.825, + "args": { + "External id": 228168,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115431430.841, "dur": 27.182, + "args": { + "External id": 228169,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 6968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115431436.246, "dur": 2.366, + "args": { + "External id": 228170,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 6969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115431460.455, "dur": 47.736, + "args": { + "External id": 228171,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 6970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115431510.855, "dur": 29.443, + "args": { + "External id": 228172,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 6971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115431543.865, "dur": 29.803, + "args": { + "External id": 228173,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 6972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115431575.463, "dur": 24.646, + "args": { + "External id": 228174,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 6973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115431602.762, "dur": 23.498, + "args": { + "External id": 228175,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 6974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115431605.023, "dur": 1.887, + "args": { + "External id": 228176,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 6975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115431609.479, "dur": 0.751, + "args": { + "External id": 228177,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 6976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115431628.161, "dur": 14.197, + "args": { + "External id": 228178,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 6977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115431643.506, "dur": 44.752, + "args": { + "External id": 228179,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 6978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115431699.701, "dur": 2.871, + "args": { + "External id": 228180,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 6979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115431713.037, "dur": 4.253, + "args": { + "External id": 228181,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 6980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115431715.763, "dur": 0.693, + "args": { + "External id": 228182,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 6981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115431794.033, "dur": 53.743, + "args": { + "External id": 228183,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 6982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115431852.920, "dur": 5.933, + "args": { + "External id": 228184,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 6983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115431856.127, "dur": 1.596, + "args": { + "External id": 228185,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "8388608"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 6984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115431860.772, "dur": 26.970, + "args": { + "External id": 228186,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 6985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115431892.301, "dur": 12.351, + "args": { + "External id": 228187,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 6986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115431899.331, "dur": 4.573, + "args": { + "External id": 228188,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 6987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115431902.351, "dur": 1.263, + "args": { + "External id": 228189,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 6988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115431907.601, "dur": 44.522, + "args": { + "External id": 228190,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 6989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115431908.560, "dur": 42.895, + "args": { + "External id": 228191,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 6990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115431955.639, "dur": 16.379, + "args": { + "External id": 228192,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 6991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115431977.524, "dur": 4.244, + "args": { + "External id": 228193,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 6992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115431980.041, "dur": 0.874, + "args": { + "External id": 228194,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 6993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115431986.169, "dur": 52.307, + "args": { + "External id": 228195,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 6994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115431987.739, "dur": 6.937, + "args": { + "External id": 228196,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 6995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115431988.597, "dur": 5.423, + "args": { + "External id": 228197,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 6996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115431990.424, "dur": 3.399, + "args": { + "External id": 228198,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 6997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115431995.313, "dur": 42.834, + "args": { + "External id": 228199,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 6998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115431996.258, "dur": 41.125, + "args": { + "External id": 228200,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 6999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115432043.072, "dur": 3.809, + "args": { + "External id": 228201,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115432045.199, "dur": 0.642, + "args": { + "External id": 228202,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115432052.783, "dur": 1.429, + "args": { + "External id": 228203,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115432061.672, "dur": 6.997, + "args": { + "External id": 228204,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115432064.493, "dur": 3.920, + "args": { + "External id": 228205,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115432155.793, "dur": 184.277, + "args": { + "External id": 228206,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115432158.202, "dur": 2.165, + "args": { + "External id": 228207,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115432162.016, "dur": 177.550, + "args": { + "External id": 228208,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115432163.993, "dur": 0.516, + "args": { + "External id": 228209,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115432168.189, "dur": 19.842, + "args": { + "External id": 228210,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115432189.913, "dur": 3.507, + "args": { + "External id": 228211,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115432192.127, "dur": 1.038, + "args": { + "External id": 228212,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115432194.317, "dur": 23.968, + "args": { + "External id": 228213,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115432195.625, "dur": 3.659, + "args": { + "External id": 228214,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115432200.960, "dur": 17.081, + "args": { + "External id": 228215,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115432204.113, "dur": 2.688, + "args": { + "External id": 228216,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115432220.026, "dur": 19.457, + "args": { + "External id": 228217,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115432240.925, "dur": 12.361, + "args": { + "External id": 228218,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115432255.838, "dur": 19.915, + "args": { + "External id": 228219,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115432277.260, "dur": 12.701, + "args": { + "External id": 228220,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115432292.243, "dur": 21.044, + "args": { + "External id": 228221,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115432294.748, "dur": 1.581, + "args": { + "External id": 228222,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115432299.029, "dur": 1.237, + "args": { + "External id": 228223,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115432315.110, "dur": 11.343, + "args": { + "External id": 228224,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115432327.617, "dur": 10.386, + "args": { + "External id": 228225,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115432345.937, "dur": 1.739, + "args": { + "External id": 228226,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115432356.587, "dur": 3.653, + "args": { + "External id": 228227,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115432358.913, "dur": 0.514, + "args": { + "External id": 228228,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115432422.848, "dur": 38.853, + "args": { + "External id": 228229,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115432465.925, "dur": 5.133, + "args": { + "External id": 228230,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115432469.136, "dur": 0.913, + "args": { + "External id": 228231,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115432472.600, "dur": 39.920, + "args": { + "External id": 228232,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115432518.527, "dur": 7.689, + "args": { + "External id": 228233,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115432519.758, "dur": 5.588, + "args": { + "External id": 228234,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115432522.153, "dur": 2.952, + "args": { + "External id": 228235,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115432529.140, "dur": 45.325, + "args": { + "External id": 228236,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115432530.491, "dur": 43.358, + "args": { + "External id": 228237,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115432578.124, "dur": 15.230, + "args": { + "External id": 228238,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115432599.267, "dur": 4.595, + "args": { + "External id": 228239,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115432601.827, "dur": 1.033, + "args": { + "External id": 228240,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "25165824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115432608.212, "dur": 83.201, + "args": { + "External id": 228241,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115432609.236, "dur": 5.097, + "args": { + "External id": 228242,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115432610.353, "dur": 3.221, + "args": { + "External id": 228243,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115432612.210, "dur": 1.203, + "args": { + "External id": 228244,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115432615.302, "dur": 75.534, + "args": { + "External id": 228245,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115432616.295, "dur": 73.552, + "args": { + "External id": 228246,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115432697.264, "dur": 5.591, + "args": { + "External id": 228247,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115432700.336, "dur": 1.095, + "args": { + "External id": 228248,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115432709.784, "dur": 1.802, + "args": { + "External id": 228249,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115432719.649, "dur": 8.338, + "args": { + "External id": 228250,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115432722.336, "dur": 5.281, + "args": { + "External id": 228251,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115432817.903, "dur": 180.103, + "args": { + "External id": 228252,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115432820.014, "dur": 2.262, + "args": { + "External id": 228253,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115432826.478, "dur": 170.997, + "args": { + "External id": 228254,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115432828.258, "dur": 0.728, + "args": { + "External id": 228255,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115432830.205, "dur": 21.743, + "args": { + "External id": 228256,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115432853.570, "dur": 6.020, + "args": { + "External id": 228257,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115432855.863, "dur": 3.427, + "args": { + "External id": 228258,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115432860.962, "dur": 21.955, + "args": { + "External id": 228259,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115432862.377, "dur": 1.590, + "args": { + "External id": 228260,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115432866.023, "dur": 16.659, + "args": { + "External id": 228261,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115432869.338, "dur": 2.842, + "args": { + "External id": 228262,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115432884.676, "dur": 20.191, + "args": { + "External id": 228263,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115432906.627, "dur": 11.885, + "args": { + "External id": 228264,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115432921.474, "dur": 13.644, + "args": { + "External id": 228265,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115432936.760, "dur": 12.074, + "args": { + "External id": 228266,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115432950.659, "dur": 21.823, + "args": { + "External id": 228267,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115432952.643, "dur": 2.167, + "args": { + "External id": 228268,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115432957.514, "dur": 3.229, + "args": { + "External id": 228269,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115432974.269, "dur": 10.977, + "args": { + "External id": 228270,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115432986.411, "dur": 10.299, + "args": { + "External id": 228271,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115433003.794, "dur": 1.683, + "args": { + "External id": 228272,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115433014.470, "dur": 3.615, + "args": { + "External id": 228273,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115433016.684, "dur": 0.547, + "args": { + "External id": 228274,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115433085.766, "dur": 47.615, + "args": { + "External id": 228275,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115433138.543, "dur": 5.150, + "args": { + "External id": 228276,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115433141.619, "dur": 1.053, + "args": { + "External id": 228277,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "25165824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115433145.304, "dur": 24.624, + "args": { + "External id": 228278,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115433174.303, "dur": 6.397, + "args": { + "External id": 228279,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115433175.774, "dur": 4.212, + "args": { + "External id": 228280,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115433178.255, "dur": 1.468, + "args": { + "External id": 228281,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115433183.358, "dur": 41.546, + "args": { + "External id": 228282,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115433184.753, "dur": 39.407, + "args": { + "External id": 228283,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115433228.445, "dur": 13.472, + "args": { + "External id": 228284,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115433247.366, "dur": 4.353, + "args": { + "External id": 228285,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115433250.016, "dur": 0.884, + "args": { + "External id": 228286,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115433255.690, "dur": 47.547, + "args": { + "External id": 228287,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115433256.865, "dur": 5.026, + "args": { + "External id": 228288,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115433257.876, "dur": 3.384, + "args": { + "External id": 228289,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115433259.898, "dur": 1.239, + "args": { + "External id": 228290,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115433262.739, "dur": 40.137, + "args": { + "External id": 228291,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115433263.599, "dur": 38.654, + "args": { + "External id": 228292,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115433307.206, "dur": 4.138, + "args": { + "External id": 228293,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115433309.594, "dur": 0.693, + "args": { + "External id": 228294,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115433316.973, "dur": 1.485, + "args": { + "External id": 228295,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115433325.481, "dur": 6.482, + "args": { + "External id": 228296,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115433327.915, "dur": 3.738, + "args": { + "External id": 228297,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115433414.413, "dur": 195.510, + "args": { + "External id": 228298,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115433418.441, "dur": 2.261, + "args": { + "External id": 228299,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115433422.421, "dur": 187.040, + "args": { + "External id": 228300,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115433423.842, "dur": 0.369, + "args": { + "External id": 228301,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115433425.529, "dur": 18.421, + "args": { + "External id": 228302,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115433445.686, "dur": 5.557, + "args": { + "External id": 228303,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115433449.976, "dur": 1.050, + "args": { + "External id": 228304,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115433452.652, "dur": 20.591, + "args": { + "External id": 228305,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115433454.024, "dur": 1.561, + "args": { + "External id": 228306,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115433457.203, "dur": 15.783, + "args": { + "External id": 228307,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115433460.083, "dur": 2.114, + "args": { + "External id": 228308,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115433474.823, "dur": 36.791, + "args": { + "External id": 228309,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115433514.127, "dur": 14.887, + "args": { + "External id": 228310,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115433532.146, "dur": 13.650, + "args": { + "External id": 228311,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115433547.080, "dur": 12.025, + "args": { + "External id": 228312,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115433561.016, "dur": 22.891, + "args": { + "External id": 228313,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115433566.030, "dur": 1.684, + "args": { + "External id": 228314,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115433570.266, "dur": 0.679, + "args": { + "External id": 228315,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115433585.755, "dur": 11.025, + "args": { + "External id": 228316,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115433597.865, "dur": 10.289, + "args": { + "External id": 228317,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115433616.914, "dur": 2.534, + "args": { + "External id": 228318,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115433641.523, "dur": 3.466, + "args": { + "External id": 228319,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115433643.828, "dur": 0.523, + "args": { + "External id": 228320,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115433753.227, "dur": 49.831, + "args": { + "External id": 228321,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115433808.515, "dur": 6.071, + "args": { + "External id": 228322,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115433812.070, "dur": 1.048, + "args": { + "External id": 228323,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115433816.107, "dur": 24.360, + "args": { + "External id": 228324,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115433845.318, "dur": 8.700, + "args": { + "External id": 228325,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115433847.049, "dur": 6.251, + "args": { + "External id": 228326,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115433849.601, "dur": 3.443, + "args": { + "External id": 228327,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115433856.592, "dur": 44.167, + "args": { + "External id": 228328,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115433857.992, "dur": 42.155, + "args": { + "External id": 228329,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115433904.128, "dur": 14.921, + "args": { + "External id": 228330,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115433924.889, "dur": 4.098, + "args": { + "External id": 228331,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115433927.161, "dur": 0.900, + "args": { + "External id": 228332,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "41943040"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115433933.453, "dur": 47.142, + "args": { + "External id": 228333,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115433934.740, "dur": 4.035, + "args": { + "External id": 228334,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115433935.554, "dur": 2.639, + "args": { + "External id": 228335,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115433937.227, "dur": 0.842, + "args": { + "External id": 228336,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115433939.843, "dur": 40.344, + "args": { + "External id": 228337,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115433940.639, "dur": 39.019, + "args": { + "External id": 228338,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115433984.244, "dur": 4.003, + "args": { + "External id": 228339,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115433986.204, "dur": 1.033, + "args": { + "External id": 228340,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115433994.371, "dur": 1.858, + "args": { + "External id": 228341,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115434004.656, "dur": 7.531, + "args": { + "External id": 228342,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115434007.308, "dur": 4.575, + "args": { + "External id": 228343,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115434096.940, "dur": 292.974, + "args": { + "External id": 228344,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115434099.322, "dur": 2.142, + "args": { + "External id": 228345,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115434105.598, "dur": 283.775, + "args": { + "External id": 228346,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115434107.318, "dur": 0.393, + "args": { + "External id": 228347,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115434109.284, "dur": 20.549, + "args": { + "External id": 228348,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115434131.572, "dur": 5.662, + "args": { + "External id": 228349,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115434133.958, "dur": 3.020, + "args": { + "External id": 228350,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115434138.698, "dur": 56.060, + "args": { + "External id": 228351,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115434140.190, "dur": 1.768, + "args": { + "External id": 228352,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115434175.843, "dur": 18.615, + "args": { + "External id": 228353,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115434179.451, "dur": 2.547, + "args": { + "External id": 228354,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115434196.482, "dur": 40.111, + "args": { + "External id": 228355,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115434238.275, "dur": 41.369, + "args": { + "External id": 228356,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115434282.531, "dur": 25.442, + "args": { + "External id": 228357,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115434309.588, "dur": 26.933, + "args": { + "External id": 228358,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115434338.602, "dur": 22.523, + "args": { + "External id": 228359,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115434340.502, "dur": 1.670, + "args": { + "External id": 228360,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115434344.560, "dur": 0.807, + "args": { + "External id": 228361,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115434362.902, "dur": 13.049, + "args": { + "External id": 228362,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115434377.333, "dur": 11.299, + "args": { + "External id": 228363,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115434395.966, "dur": 1.514, + "args": { + "External id": 228364,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115434405.892, "dur": 3.240, + "args": { + "External id": 228365,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115434407.989, "dur": 0.290, + "args": { + "External id": 228366,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115434470.766, "dur": 64.376, + "args": { + "External id": 228367,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115434541.737, "dur": 6.185, + "args": { + "External id": 228368,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115434545.057, "dur": 1.381, + "args": { + "External id": 228369,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "41943040"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115434549.368, "dur": 25.924, + "args": { + "External id": 228370,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115434579.981, "dur": 6.358, + "args": { + "External id": 228371,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115434581.975, "dur": 3.620, + "args": { + "External id": 228372,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115434584.219, "dur": 1.157, + "args": { + "External id": 228373,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115434589.135, "dur": 43.233, + "args": { + "External id": 228374,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115434590.266, "dur": 41.435, + "args": { + "External id": 228375,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115434635.720, "dur": 49.055, + "args": { + "External id": 228376,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115434693.132, "dur": 4.861, + "args": { + "External id": 228377,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115434696.082, "dur": 0.836, + "args": { + "External id": 228378,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115434702.781, "dur": 53.147, + "args": { + "External id": 228379,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115434703.780, "dur": 4.527, + "args": { + "External id": 228380,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115434704.591, "dur": 3.064, + "args": { + "External id": 228381,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115434706.432, "dur": 1.071, + "args": { + "External id": 228382,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115434708.921, "dur": 46.641, + "args": { + "External id": 228383,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115434709.650, "dur": 45.256, + "args": { + "External id": 228384,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115434760.106, "dur": 3.971, + "args": { + "External id": 228385,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115434762.092, "dur": 0.870, + "args": { + "External id": 228386,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115434770.920, "dur": 1.764, + "args": { + "External id": 228387,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115434780.134, "dur": 9.027, + "args": { + "External id": 228388,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115434783.007, "dur": 5.809, + "args": { + "External id": 228389,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115434877.129, "dur": 194.051, + "args": { + "External id": 228390,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115434879.676, "dur": 2.027, + "args": { + "External id": 228391,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115434883.229, "dur": 187.501, + "args": { + "External id": 228392,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115434885.408, "dur": 0.389, + "args": { + "External id": 228393,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115434887.298, "dur": 25.931, + "args": { + "External id": 228394,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115434915.257, "dur": 2.828, + "args": { + "External id": 228395,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115434917.009, "dur": 0.733, + "args": { + "External id": 228396,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115434919.188, "dur": 24.758, + "args": { + "External id": 228397,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115434920.443, "dur": 1.747, + "args": { + "External id": 228398,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115434923.589, "dur": 20.024, + "args": { + "External id": 228399,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115434929.053, "dur": 2.640, + "args": { + "External id": 228400,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115434945.700, "dur": 20.081, + "args": { + "External id": 228401,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115434967.290, "dur": 14.314, + "args": { + "External id": 228402,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115434991.637, "dur": 13.676, + "args": { + "External id": 228403,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115435006.830, "dur": 15.662, + "args": { + "External id": 228404,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115435024.501, "dur": 20.214, + "args": { + "External id": 228405,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115435026.810, "dur": 1.966, + "args": { + "External id": 228406,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115435030.992, "dur": 0.811, + "args": { + "External id": 228407,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115435046.565, "dur": 11.156, + "args": { + "External id": 228408,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115435058.876, "dur": 10.333, + "args": { + "External id": 228409,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115435076.931, "dur": 1.674, + "args": { + "External id": 228410,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115435087.315, "dur": 3.539, + "args": { + "External id": 228411,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115435089.374, "dur": 0.705, + "args": { + "External id": 228412,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115435150.669, "dur": 41.380, + "args": { + "External id": 228413,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115435196.462, "dur": 6.795, + "args": { + "External id": 228414,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115435199.240, "dur": 3.044, + "args": { + "External id": 228415,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115435204.584, "dur": 22.715, + "args": { + "External id": 228416,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115435231.384, "dur": 5.397, + "args": { + "External id": 228417,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115435232.599, "dur": 3.517, + "args": { + "External id": 228418,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115435234.835, "dur": 1.096, + "args": { + "External id": 228419,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115435239.299, "dur": 40.196, + "args": { + "External id": 228420,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115435240.647, "dur": 38.353, + "args": { + "External id": 228421,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115435282.817, "dur": 15.424, + "args": { + "External id": 228422,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115435303.382, "dur": 3.943, + "args": { + "External id": 228423,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115435305.661, "dur": 0.872, + "args": { + "External id": 228424,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "58720256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115435310.872, "dur": 46.501, + "args": { + "External id": 228425,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115435311.757, "dur": 4.573, + "args": { + "External id": 228426,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115435312.738, "dur": 2.913, + "args": { + "External id": 228427,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115435314.466, "dur": 1.036, + "args": { + "External id": 228428,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115435317.328, "dur": 39.688, + "args": { + "External id": 228429,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115435317.800, "dur": 38.596, + "args": { + "External id": 228430,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115435360.988, "dur": 3.572, + "args": { + "External id": 228431,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115435362.891, "dur": 0.676, + "args": { + "External id": 228432,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115435369.350, "dur": 1.194, + "args": { + "External id": 228433,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115435377.607, "dur": 5.909, + "args": { + "External id": 228434,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115435379.719, "dur": 3.529, + "args": { + "External id": 228435,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115435457.701, "dur": 246.603, + "args": { + "External id": 228436,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115435459.630, "dur": 4.109, + "args": { + "External id": 228437,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115435465.303, "dur": 238.396, + "args": { + "External id": 228438,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115435466.843, "dur": 0.353, + "args": { + "External id": 228439,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115435468.300, "dur": 19.354, + "args": { + "External id": 228440,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115435489.019, "dur": 23.779, + "args": { + "External id": 228441,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115435511.165, "dur": 1.133, + "args": { + "External id": 228442,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115435513.760, "dur": 25.965, + "args": { + "External id": 228443,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115435514.977, "dur": 2.443, + "args": { + "External id": 228444,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115435518.827, "dur": 20.579, + "args": { + "External id": 228445,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115435522.375, "dur": 2.592, + "args": { + "External id": 228446,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115435541.000, "dur": 20.969, + "args": { + "External id": 228447,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115435563.203, "dur": 13.048, + "args": { + "External id": 228448,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115435579.131, "dur": 15.126, + "args": { + "External id": 228449,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115435595.554, "dur": 13.056, + "args": { + "External id": 228450,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115435610.323, "dur": 23.470, + "args": { + "External id": 228451,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115435612.249, "dur": 1.889, + "args": { + "External id": 228452,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115435616.390, "dur": 2.942, + "args": { + "External id": 228453,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115435635.430, "dur": 12.476, + "args": { + "External id": 228454,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115435649.033, "dur": 52.546, + "args": { + "External id": 228455,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115435712.781, "dur": 2.171, + "args": { + "External id": 228456,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115435724.958, "dur": 4.358, + "args": { + "External id": 228457,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115435727.745, "dur": 0.719, + "args": { + "External id": 228458,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115435802.644, "dur": 51.119, + "args": { + "External id": 228459,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115435858.490, "dur": 5.989, + "args": { + "External id": 228460,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115435861.931, "dur": 1.480, + "args": { + "External id": 228461,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "58720256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115435866.052, "dur": 26.214, + "args": { + "External id": 228462,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115435897.228, "dur": 6.540, + "args": { + "External id": 228463,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115435898.843, "dur": 4.272, + "args": { + "External id": 228464,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115435901.264, "dur": 1.648, + "args": { + "External id": 228465,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115435906.336, "dur": 41.363, + "args": { + "External id": 228466,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115435907.610, "dur": 39.517, + "args": { + "External id": 228467,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115435951.112, "dur": 14.596, + "args": { + "External id": 228468,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115435970.555, "dur": 24.618, + "args": { + "External id": 228469,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 7268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115435973.443, "dur": 21.292, + "args": { + "External id": 228470,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115435978.573, "dur": 0.949, + "args": { + "External id": 228471,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 7270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115436000.811, "dur": 27.286, + "args": { + "External id": 228472,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[32000, 1024], [], [], [], [], []], "Ev Idx": 7271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115436003.237, "dur": 24.625, + "args": { + "External id": 228473,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], [], []], "Input Dims": [[32000, 1024], [], [], [], [], [], []], "Ev Idx": 7272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115436008.099, "dur": 4.272, + "args": { + "External id": 228474,"Record function id": 0, "Concrete Inputs": ["[32000, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115436013.676, "dur": 13.732, + "args": { + "External id": 228475,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 4183440, + "ts": 667115436044.705, "dur": 6.028, + "args": { + "External id": 228476,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 7275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 4183440, + "ts": 667115436047.544, "dur": 2.975, + "args": { + "External id": 228477,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 7276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 4183440, + "ts": 667115436051.815, "dur": 1.440, + "args": { + "External id": 228478,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 4183440, + "ts": 667115436052.689, "dur": 0.480, + "args": { + "External id": 228479,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115436095.228, "dur": 21.174, + "args": { + "External id": 228480,"Sequence number": 2757933, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 7279 + } + }, + { + "ph": "s", "id": 23, "pid": 4183440, "tid": 4183440, "ts": 667115436095.228, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115436122.200, "dur": 5.686, + "args": { + "External id": 228481,"Sequence number": 2757934, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 4, 4096], [], [], [], []], "Ev Idx": 7280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115436125.752, "dur": 0.925, + "args": { + "External id": 228482,"Record function id": 0, "Concrete Inputs": ["", "[16, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 7281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183440, "tid": 4183440, + "ts": 667115436130.292, "dur": 6.935, + "args": { + "External id": 228483,"Sequence number": 2757934, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "1"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[16, 4, 4096], [], []], "Ev Idx": 7282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115436135.123, "dur": 0.963, + "args": { + "External id": 228484,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "2"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 7283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115436138.510, "dur": 3.588, + "args": { + "External id": 228485,"Sequence number": 2757934, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], []], "Ev Idx": 7284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115436140.597, "dur": 0.929, + "args": { + "External id": 228486,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "2"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 7285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115436146.183, "dur": 6.644, + "args": { + "External id": 228487,"Sequence number": 2757934, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], []], "Ev Idx": 7286 + } + }, + { + "ph": "s", "id": 22, "pid": 4183440, "tid": 4183440, "ts": 667115436146.183, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115436150.202, "dur": 1.207, + "args": { + "External id": 228488,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "[16777216, 4096, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 7287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115436153.759, "dur": 5.602, + "args": { + "External id": 228489,"Sequence number": 2757935, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], []], "Ev Idx": 7288 + } + }, + { + "ph": "s", "id": 21, "pid": 4183440, "tid": 4183440, "ts": 667115436153.759, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115436157.979, "dur": 0.625, + "args": { + "External id": 228490,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "[16777216, 4096, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 7289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183440, "tid": 4183440, + "ts": 667115436160.327, "dur": 5.799, + "args": { + "External id": 228491,"Sequence number": 2757936, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], []], "Input Dims": [[16, 4096, 4, 1024], [], []], "Ev Idx": 7290 + } + }, + { + "ph": "s", "id": 20, "pid": 4183440, "tid": 4183440, "ts": 667115436160.327, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115436164.124, "dur": 1.147, + "args": { + "External id": 228492,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[16777216, 4096, 1]", "1024"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 7291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115436167.104, "dur": 5.304, + "args": { + "External id": 228493,"Sequence number": 2757937, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], [], []], "Ev Idx": 7292 + } + }, + { + "ph": "s", "id": 19, "pid": 4183440, "tid": 4183440, "ts": 667115436167.104, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115436170.479, "dur": 1.256, + "args": { + "External id": 228494,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[16777216, 4096, 1]", "1024"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], []], "Ev Idx": 7293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183440, "tid": 4183440, + "ts": 667115436176.055, "dur": 30.474, + "args": { + "External id": 228495,"Sequence number": 2757938, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 7294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 4183440, + "ts": 667115436177.616, "dur": 28.712, + "args": { + "External id": 228496,"Sequence number": 2757938, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 7295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115436180.495, "dur": 7.495, + "args": { + "External id": 228497,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], []], "Ev Idx": 7296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115436183.270, "dur": 4.194, + "args": { + "External id": 228498,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115436189.303, "dur": 16.653, + "args": { + "External id": 228499,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 7298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115436233.225, "dur": 5.715, + "args": { + "External id": 228500,"Sequence number": 2757938, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 7299 + } + }, + { + "ph": "s", "id": 18, "pid": 4183440, "tid": 4183440, "ts": 667115436233.225, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115436241.768, "dur": 1.158, + "args": { + "External id": 228501,"Sequence number": 2757939, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 7300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115436274.400, "dur": 22052.790, + "args": { + "External id": 228502,"Sequence number": 2757939, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536], [32000, 1024], [], [], [], [], []], "Ev Idx": 7301 + } + }, + { + "ph": "s", "id": 17, "pid": 4183440, "tid": 4183440, "ts": 667115436274.400, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183440, "tid": 4183440, + "ts": 667115436288.051, "dur": 59.471, + "args": { + "External id": 228503,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 7302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 4183440, + "ts": 667115436288.896, "dur": 58.417, + "args": { + "External id": 228504,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 7303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115436291.139, "dur": 33.591, + "args": { + "External id": 228505,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 7304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115436298.086, "dur": 26.101, + "args": { + "External id": 228506,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115436325.526, "dur": 21.308, + "args": { + "External id": 228507,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [4096, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 7306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 4183440, "tid": 4183440, + "ts": 667115436367.278, "dur": 28.206, + "args": { + "External id": 228508,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 7307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115436368.293, "dur": 8.310, + "args": { + "External id": 228509,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 7308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115436372.221, "dur": 4.067, + "args": { + "External id": 228510,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 4183440, + "ts": 667115436377.830, "dur": 17.432, + "args": { + "External id": 228511,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 7310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115436379.827, "dur": 14.969, + "args": { + "External id": 228512,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 7311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 4183440, "tid": 4183440, + "ts": 667115436398.843, "dur": 19.465, + "args": { + "External id": 228513,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[32000, 1024], [], [], [], [], []], "Ev Idx": 7312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115436399.677, "dur": 4.923, + "args": { + "External id": 228514,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[32000, 1024], [], [], [], [], []], "Ev Idx": 7313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115436401.272, "dur": 3.053, + "args": { + "External id": 228515,"Record function id": 0, "Concrete Inputs": ["[32000, 1024]", "[1024, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 4183440, + "ts": 667115436405.210, "dur": 12.898, + "args": { + "External id": 228516,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115436405.918, "dur": 11.803, + "args": { + "External id": 228517,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1024, 1], []], "Input Dims": [[32000, 1024], []], "Ev Idx": 7316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 4183440, + "ts": 667115436424.465, "dur": 19.143, + "args": { + "External id": 228518,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 7317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115436428.694, "dur": 2.675, + "args": { + "External id": 228519,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 4183440, + "ts": 667115436432.310, "dur": 11.023, + "args": { + "External id": 228520,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[65536]], "Ev Idx": 7319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115436433.288, "dur": 9.748, + "args": { + "External id": 228521,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 7320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 4183440, "tid": 4183440, + "ts": 667115436448.866, "dur": 22.010, + "args": { + "External id": 228522,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 7321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115436473.726, "dur": 72.994, + "args": { + "External id": 228523,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 7322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115436475.670, "dur": 70.558, + "args": { + "External id": 228524,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115436480.485, "dur": 0.979, + "args": { + "External id": 228525,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 7324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115436483.383, "dur": 47.420, + "args": { + "External id": 228526,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115436485.430, "dur": 45.173, + "args": { + "External id": 228527,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[65536], [], [], [], [], [], []], "Ev Idx": 7326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115436489.766, "dur": 23.233, + "args": { + "External id": 228528,"Record function id": 0, "Concrete Inputs": ["[65536]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115436515.378, "dur": 14.776, + "args": { + "External id": 228529,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[65536], [65536], []], "Ev Idx": 7328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 4183440, "tid": 4183440, + "ts": 667115436551.220, "dur": 16234.756, + "args": { + "External id": 228530,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 7329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 4183440, "tid": 4183440, + "ts": 667115436552.790, "dur": 16231.161, + "args": { + "External id": 228531,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 7330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115452798.556, "dur": 7.329, + "args": { + "External id": 228532,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115452802.840, "dur": 1.418, + "args": { + "External id": 228533,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115452811.768, "dur": 103.120, + "args": { + "External id": 228534,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115452813.603, "dur": 7.422, + "args": { + "External id": 228535,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115452816.146, "dur": 3.841, + "args": { + "External id": 228536,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115452818.633, "dur": 1.085, + "args": { + "External id": 228537,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115452822.854, "dur": 91.258, + "args": { + "External id": 228538,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115452824.829, "dur": 88.490, + "args": { + "External id": 228539,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115452918.603, "dur": 4.632, + "args": { + "External id": 228540,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115452921.197, "dur": 0.777, + "args": { + "External id": 228541,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115452931.128, "dur": 2.462, + "args": { + "External id": 228542,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115452942.895, "dur": 6.420, + "args": { + "External id": 228543,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115452945.211, "dur": 3.797, + "args": { + "External id": 228544,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115453071.714, "dur": 208.204, + "args": { + "External id": 228545,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115453075.143, "dur": 2.420, + "args": { + "External id": 228546,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115453079.852, "dur": 199.496, + "args": { + "External id": 228547,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115453084.483, "dur": 0.453, + "args": { + "External id": 228548,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115453086.462, "dur": 24.230, + "args": { + "External id": 228549,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115453112.821, "dur": 4.119, + "args": { + "External id": 228550,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115453115.600, "dur": 0.923, + "args": { + "External id": 228551,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115453118.174, "dur": 39.667, + "args": { + "External id": 228552,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115453136.480, "dur": 1.431, + "args": { + "External id": 228553,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115453139.615, "dur": 17.977, + "args": { + "External id": 228554,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115453143.113, "dur": 2.911, + "args": { + "External id": 228555,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115453159.664, "dur": 21.713, + "args": { + "External id": 228556,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115453183.493, "dur": 14.390, + "args": { + "External id": 228557,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115453200.920, "dur": 14.871, + "args": { + "External id": 228558,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115453217.500, "dur": 13.282, + "args": { + "External id": 228559,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115453232.819, "dur": 20.840, + "args": { + "External id": 228560,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115453235.046, "dur": 1.646, + "args": { + "External id": 228561,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115453239.755, "dur": 0.843, + "args": { + "External id": 228562,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115453255.320, "dur": 11.366, + "args": { + "External id": 228563,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115453268.403, "dur": 10.213, + "args": { + "External id": 228564,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115453286.302, "dur": 2.100, + "args": { + "External id": 228565,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115453294.108, "dur": 4.093, + "args": { + "External id": 228566,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115453296.507, "dur": 0.772, + "args": { + "External id": 228567,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115453364.403, "dur": 49.764, + "args": { + "External id": 228568,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115453419.080, "dur": 8.310, + "args": { + "External id": 228569,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115453421.855, "dur": 2.538, + "args": { + "External id": 228570,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115453429.347, "dur": 24.065, + "args": { + "External id": 228571,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115453458.709, "dur": 6.275, + "args": { + "External id": 228572,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115453460.451, "dur": 3.779, + "args": { + "External id": 228573,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115453463.004, "dur": 1.016, + "args": { + "External id": 228574,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115453468.107, "dur": 62.511, + "args": { + "External id": 228575,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115453469.554, "dur": 60.048, + "args": { + "External id": 228576,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115453535.991, "dur": 15.874, + "args": { + "External id": 228577,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115453558.301, "dur": 4.921, + "args": { + "External id": 228578,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115453561.074, "dur": 1.204, + "args": { + "External id": 228579,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "8388608"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115453568.022, "dur": 52.610, + "args": { + "External id": 228580,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115453569.073, "dur": 5.192, + "args": { + "External id": 228581,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115453570.251, "dur": 3.429, + "args": { + "External id": 228582,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115453572.347, "dur": 1.078, + "args": { + "External id": 228583,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115453574.885, "dur": 45.342, + "args": { + "External id": 228584,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115453575.690, "dur": 43.994, + "args": { + "External id": 228585,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115453624.330, "dur": 3.453, + "args": { + "External id": 228586,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115453626.224, "dur": 0.498, + "args": { + "External id": 228587,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115453634.011, "dur": 1.880, + "args": { + "External id": 228588,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115453643.557, "dur": 7.072, + "args": { + "External id": 228589,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115453646.237, "dur": 4.135, + "args": { + "External id": 228590,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115453786.249, "dur": 255.487, + "args": { + "External id": 228591,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115453788.866, "dur": 5.514, + "args": { + "External id": 228592,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115453796.583, "dur": 244.516, + "args": { + "External id": 228593,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115453798.363, "dur": 0.609, + "args": { + "External id": 228594,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115453800.345, "dur": 22.382, + "args": { + "External id": 228595,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115453824.629, "dur": 5.955, + "args": { + "External id": 228596,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115453829.460, "dur": 0.859, + "args": { + "External id": 228597,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115453831.701, "dur": 22.200, + "args": { + "External id": 228598,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115453832.669, "dur": 1.512, + "args": { + "External id": 228599,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115453836.052, "dur": 17.610, + "args": { + "External id": 228600,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115453839.589, "dur": 3.066, + "args": { + "External id": 228601,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115453855.398, "dur": 20.975, + "args": { + "External id": 228602,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115453878.149, "dur": 12.633, + "args": { + "External id": 228603,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115453893.592, "dur": 15.178, + "args": { + "External id": 228604,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115453910.369, "dur": 12.880, + "args": { + "External id": 228605,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115453925.084, "dur": 30.431, + "args": { + "External id": 228606,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115453927.211, "dur": 1.786, + "args": { + "External id": 228607,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115453931.247, "dur": 3.394, + "args": { + "External id": 228608,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115453957.214, "dur": 37.880, + "args": { + "External id": 228609,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115453996.487, "dur": 43.851, + "args": { + "External id": 228610,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115454047.996, "dur": 2.152, + "args": { + "External id": 228611,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115454059.237, "dur": 3.705, + "args": { + "External id": 228612,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115454061.690, "dur": 0.368, + "args": { + "External id": 228613,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115454127.714, "dur": 48.320, + "args": { + "External id": 228614,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115454180.887, "dur": 4.938, + "args": { + "External id": 228615,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115454183.849, "dur": 0.895, + "args": { + "External id": 228616,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "8388608"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115454187.171, "dur": 26.292, + "args": { + "External id": 228617,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115454217.893, "dur": 5.791, + "args": { + "External id": 228618,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115454219.429, "dur": 3.571, + "args": { + "External id": 228619,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115454221.463, "dur": 1.308, + "args": { + "External id": 228620,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115454226.340, "dur": 40.737, + "args": { + "External id": 228621,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115454227.727, "dur": 38.907, + "args": { + "External id": 228622,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115454270.442, "dur": 15.084, + "args": { + "External id": 228623,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115454291.036, "dur": 3.877, + "args": { + "External id": 228624,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115454293.382, "dur": 0.762, + "args": { + "External id": 228625,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115454299.672, "dur": 61.855, + "args": { + "External id": 228626,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115454300.959, "dur": 4.017, + "args": { + "External id": 228627,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115454301.900, "dur": 2.512, + "args": { + "External id": 228628,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115454303.331, "dur": 0.931, + "args": { + "External id": 228629,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115454318.845, "dur": 42.398, + "args": { + "External id": 228630,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115454319.658, "dur": 41.165, + "args": { + "External id": 228631,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115454365.911, "dur": 3.787, + "args": { + "External id": 228632,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115454367.967, "dur": 0.707, + "args": { + "External id": 228633,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115454375.612, "dur": 1.563, + "args": { + "External id": 228634,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115454384.895, "dur": 7.507, + "args": { + "External id": 228635,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115454386.922, "dur": 5.166, + "args": { + "External id": 228636,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115454474.755, "dur": 243.318, + "args": { + "External id": 228637,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115454476.875, "dur": 1.751, + "args": { + "External id": 228638,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115454480.019, "dur": 237.567, + "args": { + "External id": 228639,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115454481.559, "dur": 0.398, + "args": { + "External id": 228640,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115454483.288, "dur": 42.775, + "args": { + "External id": 228641,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115454528.807, "dur": 3.953, + "args": { + "External id": 228642,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115454531.422, "dur": 1.059, + "args": { + "External id": 228643,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115454533.828, "dur": 26.600, + "args": { + "External id": 228644,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115454534.963, "dur": 1.989, + "args": { + "External id": 228645,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115454538.543, "dur": 21.609, + "args": { + "External id": 228646,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115454544.247, "dur": 2.811, + "args": { + "External id": 228647,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115454561.981, "dur": 20.754, + "args": { + "External id": 228648,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115454584.418, "dur": 14.900, + "args": { + "External id": 228649,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115454601.718, "dur": 14.075, + "args": { + "External id": 228650,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115454617.267, "dur": 13.097, + "args": { + "External id": 228651,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115454632.113, "dur": 54.010, + "args": { + "External id": 228652,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115454633.934, "dur": 1.760, + "args": { + "External id": 228653,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115454638.243, "dur": 0.711, + "args": { + "External id": 228654,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115454689.266, "dur": 14.094, + "args": { + "External id": 228655,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115454704.718, "dur": 11.606, + "args": { + "External id": 228656,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115454728.806, "dur": 2.461, + "args": { + "External id": 228657,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115454741.031, "dur": 4.204, + "args": { + "External id": 228658,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115454743.860, "dur": 0.518, + "args": { + "External id": 228659,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115454815.435, "dur": 51.373, + "args": { + "External id": 228660,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115454871.941, "dur": 5.285, + "args": { + "External id": 228661,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115454875.159, "dur": 0.960, + "args": { + "External id": 228662,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115454878.635, "dur": 24.219, + "args": { + "External id": 228663,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115454907.257, "dur": 8.858, + "args": { + "External id": 228664,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115454909.093, "dur": 6.228, + "args": { + "External id": 228665,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115454911.617, "dur": 3.427, + "args": { + "External id": 228666,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115454918.937, "dur": 41.015, + "args": { + "External id": 228667,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115454920.277, "dur": 38.905, + "args": { + "External id": 228668,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115454963.654, "dur": 14.291, + "args": { + "External id": 228669,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115454983.449, "dur": 4.438, + "args": { + "External id": 228670,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115454986.144, "dur": 0.878, + "args": { + "External id": 228671,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "25165824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115454992.177, "dur": 47.003, + "args": { + "External id": 228672,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115454993.175, "dur": 4.715, + "args": { + "External id": 228673,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115454994.029, "dur": 3.182, + "args": { + "External id": 228674,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115454996.000, "dur": 1.058, + "args": { + "External id": 228675,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115454998.831, "dur": 40.047, + "args": { + "External id": 228676,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115454999.643, "dur": 38.699, + "args": { + "External id": 228677,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115455043.183, "dur": 3.948, + "args": { + "External id": 228678,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115455045.176, "dur": 0.720, + "args": { + "External id": 228679,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115455052.832, "dur": 1.632, + "args": { + "External id": 228680,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115455062.026, "dur": 7.248, + "args": { + "External id": 228681,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115455064.428, "dur": 4.473, + "args": { + "External id": 228682,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115455153.599, "dur": 175.030, + "args": { + "External id": 228683,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115455155.920, "dur": 2.339, + "args": { + "External id": 228684,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115455161.946, "dur": 166.252, + "args": { + "External id": 228685,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115455163.813, "dur": 0.395, + "args": { + "External id": 228686,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115455165.802, "dur": 19.944, + "args": { + "External id": 228687,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115455187.575, "dur": 5.088, + "args": { + "External id": 228688,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115455189.659, "dur": 2.759, + "args": { + "External id": 228689,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115455193.780, "dur": 21.284, + "args": { + "External id": 228690,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115455195.349, "dur": 2.042, + "args": { + "External id": 228691,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115455199.171, "dur": 15.579, + "args": { + "External id": 228692,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115455202.360, "dur": 2.448, + "args": { + "External id": 228693,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115455217.450, "dur": 19.260, + "args": { + "External id": 228694,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115455238.252, "dur": 12.058, + "args": { + "External id": 228695,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115455253.371, "dur": 12.781, + "args": { + "External id": 228696,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115455267.523, "dur": 11.633, + "args": { + "External id": 228697,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115455280.979, "dur": 21.791, + "args": { + "External id": 228698,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115455283.040, "dur": 1.842, + "args": { + "External id": 228699,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115455287.597, "dur": 3.187, + "args": { + "External id": 228700,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115455304.397, "dur": 11.106, + "args": { + "External id": 228701,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115455316.593, "dur": 10.453, + "args": { + "External id": 228702,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115455334.505, "dur": 1.451, + "args": { + "External id": 228703,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115455344.112, "dur": 3.372, + "args": { + "External id": 228704,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115455346.250, "dur": 0.427, + "args": { + "External id": 228705,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115455407.231, "dur": 38.071, + "args": { + "External id": 228706,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115455449.796, "dur": 4.875, + "args": { + "External id": 228707,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115455452.893, "dur": 0.890, + "args": { + "External id": 228708,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "25165824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115455455.960, "dur": 23.178, + "args": { + "External id": 228709,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115455483.342, "dur": 5.955, + "args": { + "External id": 228710,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115455484.349, "dur": 4.208, + "args": { + "External id": 228711,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115455486.763, "dur": 1.596, + "args": { + "External id": 228712,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115455510.182, "dur": 46.605, + "args": { + "External id": 228713,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115455511.502, "dur": 44.532, + "args": { + "External id": 228714,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115455560.408, "dur": 16.312, + "args": { + "External id": 228715,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115455582.579, "dur": 4.902, + "args": { + "External id": 228716,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115455585.557, "dur": 0.865, + "args": { + "External id": 228717,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115455591.814, "dur": 50.527, + "args": { + "External id": 228718,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115455592.726, "dur": 4.813, + "args": { + "External id": 228719,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115455593.640, "dur": 3.317, + "args": { + "External id": 228720,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115455595.796, "dur": 1.020, + "args": { + "External id": 228721,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115455598.362, "dur": 43.645, + "args": { + "External id": 228722,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115455599.199, "dur": 42.206, + "args": { + "External id": 228723,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115455646.072, "dur": 4.521, + "args": { + "External id": 228724,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115455648.174, "dur": 1.353, + "args": { + "External id": 228725,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115455691.270, "dur": 2.506, + "args": { + "External id": 228726,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115455702.109, "dur": 7.130, + "args": { + "External id": 228727,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115455704.574, "dur": 4.400, + "args": { + "External id": 228728,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115455802.817, "dur": 184.526, + "args": { + "External id": 228729,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115455807.481, "dur": 1.977, + "args": { + "External id": 228730,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115455811.007, "dur": 175.904, + "args": { + "External id": 228731,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115455812.609, "dur": 0.461, + "args": { + "External id": 228732,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115455814.303, "dur": 23.290, + "args": { + "External id": 228733,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115455839.258, "dur": 6.016, + "args": { + "External id": 228734,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115455843.882, "dur": 1.131, + "args": { + "External id": 228735,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115455846.327, "dur": 23.870, + "args": { + "External id": 228736,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115455847.584, "dur": 1.540, + "args": { + "External id": 228737,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115455850.927, "dur": 18.863, + "args": { + "External id": 228738,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115455853.720, "dur": 2.715, + "args": { + "External id": 228739,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115455871.610, "dur": 21.815, + "args": { + "External id": 228740,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115455894.883, "dur": 13.699, + "args": { + "External id": 228741,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115455911.203, "dur": 13.227, + "args": { + "External id": 228742,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115455926.164, "dur": 11.406, + "args": { + "External id": 228743,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115455939.383, "dur": 21.577, + "args": { + "External id": 228744,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115455943.399, "dur": 1.356, + "args": { + "External id": 228745,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115455947.515, "dur": 0.968, + "args": { + "External id": 228746,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115455962.942, "dur": 10.857, + "args": { + "External id": 228747,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115455975.258, "dur": 10.783, + "args": { + "External id": 228748,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115455993.267, "dur": 2.074, + "args": { + "External id": 228749,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115456003.961, "dur": 3.981, + "args": { + "External id": 228750,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115456006.649, "dur": 0.488, + "args": { + "External id": 228751,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115456071.288, "dur": 44.093, + "args": { + "External id": 228752,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115456119.949, "dur": 5.170, + "args": { + "External id": 228753,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115456123.042, "dur": 1.008, + "args": { + "External id": 228754,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115456126.581, "dur": 22.780, + "args": { + "External id": 228755,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115456153.463, "dur": 5.812, + "args": { + "External id": 228756,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115456154.832, "dur": 3.849, + "args": { + "External id": 228757,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115456157.222, "dur": 1.229, + "args": { + "External id": 228758,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115456162.213, "dur": 38.335, + "args": { + "External id": 228759,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115456163.411, "dur": 36.473, + "args": { + "External id": 228760,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115456203.945, "dur": 13.710, + "args": { + "External id": 228761,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115456223.042, "dur": 4.371, + "args": { + "External id": 228762,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115456225.597, "dur": 0.947, + "args": { + "External id": 228763,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "41943040"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115456231.186, "dur": 45.958, + "args": { + "External id": 228764,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115456232.691, "dur": 3.752, + "args": { + "External id": 228765,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115456233.370, "dur": 2.545, + "args": { + "External id": 228766,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115456235.084, "dur": 0.693, + "args": { + "External id": 228767,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115456237.169, "dur": 39.654, + "args": { + "External id": 228768,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115456237.889, "dur": 38.347, + "args": { + "External id": 228769,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115456280.908, "dur": 3.666, + "args": { + "External id": 228770,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115456282.785, "dur": 0.720, + "args": { + "External id": 228771,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115456290.093, "dur": 1.460, + "args": { + "External id": 228772,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115456297.789, "dur": 6.348, + "args": { + "External id": 228773,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115456299.987, "dur": 3.876, + "args": { + "External id": 228774,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115456377.370, "dur": 194.762, + "args": { + "External id": 228775,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115456381.689, "dur": 1.954, + "args": { + "External id": 228776,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115456384.963, "dur": 186.573, + "args": { + "External id": 228777,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115456386.141, "dur": 0.358, + "args": { + "External id": 228778,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115456387.444, "dur": 18.129, + "args": { + "External id": 228779,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115456406.908, "dur": 5.451, + "args": { + "External id": 228780,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115456410.821, "dur": 1.311, + "args": { + "External id": 228781,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115456413.556, "dur": 19.460, + "args": { + "External id": 228782,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115456414.758, "dur": 1.497, + "args": { + "External id": 228783,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115456417.469, "dur": 15.293, + "args": { + "External id": 228784,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115456419.792, "dur": 2.180, + "args": { + "External id": 228785,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115456434.487, "dur": 20.368, + "args": { + "External id": 228786,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115456456.310, "dur": 13.089, + "args": { + "External id": 228787,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115456472.120, "dur": 13.298, + "args": { + "External id": 228788,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115456486.593, "dur": 30.909, + "args": { + "External id": 228789,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115456520.485, "dur": 23.168, + "args": { + "External id": 228790,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115456522.610, "dur": 1.901, + "args": { + "External id": 228791,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115456526.687, "dur": 1.126, + "args": { + "External id": 228792,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115456545.457, "dur": 13.098, + "args": { + "External id": 228793,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115456559.422, "dur": 11.023, + "args": { + "External id": 228794,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115456579.189, "dur": 2.224, + "args": { + "External id": 228795,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115456590.058, "dur": 3.302, + "args": { + "External id": 228796,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115456592.082, "dur": 0.486, + "args": { + "External id": 228797,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115456703.316, "dur": 54.919, + "args": { + "External id": 228798,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115456764.072, "dur": 5.985, + "args": { + "External id": 228799,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115456767.545, "dur": 0.854, + "args": { + "External id": 228800,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "41943040"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115456771.665, "dur": 37.091, + "args": { + "External id": 228801,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115456813.816, "dur": 8.205, + "args": { + "External id": 228802,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115456815.341, "dur": 5.951, + "args": { + "External id": 228803,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115456817.734, "dur": 3.302, + "args": { + "External id": 228804,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115456824.495, "dur": 63.303, + "args": { + "External id": 228805,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115456825.985, "dur": 61.153, + "args": { + "External id": 228806,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115456891.549, "dur": 27.504, + "args": { + "External id": 228807,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115456924.587, "dur": 4.036, + "args": { + "External id": 228808,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115456926.824, "dur": 0.982, + "args": { + "External id": 228809,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115456932.755, "dur": 47.473, + "args": { + "External id": 228810,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115456933.536, "dur": 3.935, + "args": { + "External id": 228811,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115456934.504, "dur": 2.494, + "args": { + "External id": 228812,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115456936.120, "dur": 0.746, + "args": { + "External id": 228813,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115456938.408, "dur": 41.442, + "args": { + "External id": 228814,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115456939.083, "dur": 40.256, + "args": { + "External id": 228815,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115456984.195, "dur": 4.326, + "args": { + "External id": 228816,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115456986.519, "dur": 0.931, + "args": { + "External id": 228817,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115456994.142, "dur": 1.505, + "args": { + "External id": 228818,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115457003.082, "dur": 14.605, + "args": { + "External id": 228819,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115457011.010, "dur": 6.385, + "args": { + "External id": 228820,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115457102.345, "dur": 182.008, + "args": { + "External id": 228821,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115457104.525, "dur": 2.329, + "args": { + "External id": 228822,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115457108.870, "dur": 174.840, + "args": { + "External id": 228823,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115457110.236, "dur": 0.420, + "args": { + "External id": 228824,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115457111.743, "dur": 23.336, + "args": { + "External id": 228825,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115457136.850, "dur": 3.609, + "args": { + "External id": 228826,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115457139.100, "dur": 1.083, + "args": { + "External id": 228827,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115457141.296, "dur": 25.204, + "args": { + "External id": 228828,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115457142.636, "dur": 1.663, + "args": { + "External id": 228829,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115457146.018, "dur": 20.095, + "args": { + "External id": 228830,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115457151.060, "dur": 2.272, + "args": { + "External id": 228831,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115457167.996, "dur": 20.289, + "args": { + "External id": 228832,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115457189.605, "dur": 14.209, + "args": { + "External id": 228833,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115457206.539, "dur": 13.485, + "args": { + "External id": 228834,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115457221.214, "dur": 13.123, + "args": { + "External id": 228835,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115457236.162, "dur": 20.368, + "args": { + "External id": 228836,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115457238.022, "dur": 1.654, + "args": { + "External id": 228837,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115457242.200, "dur": 0.590, + "args": { + "External id": 228838,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115457258.254, "dur": 12.576, + "args": { + "External id": 228839,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115457272.039, "dur": 10.607, + "args": { + "External id": 228840,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115457290.322, "dur": 1.807, + "args": { + "External id": 228841,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115457299.798, "dur": 3.336, + "args": { + "External id": 228842,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115457301.893, "dur": 0.458, + "args": { + "External id": 228843,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115457363.647, "dur": 36.585, + "args": { + "External id": 228844,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115457404.500, "dur": 5.010, + "args": { + "External id": 228845,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115457407.726, "dur": 0.824, + "args": { + "External id": 228846,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115457410.759, "dur": 21.305, + "args": { + "External id": 228847,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115457435.913, "dur": 5.258, + "args": { + "External id": 228848,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115457437.028, "dur": 3.475, + "args": { + "External id": 228849,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115457438.914, "dur": 1.351, + "args": { + "External id": 228850,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115457443.500, "dur": 37.797, + "args": { + "External id": 228851,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115457444.947, "dur": 35.785, + "args": { + "External id": 228852,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115457484.130, "dur": 31.266, + "args": { + "External id": 228853,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115457522.975, "dur": 4.759, + "args": { + "External id": 228854,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115457525.692, "dur": 0.893, + "args": { + "External id": 228855,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "58720256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115457532.229, "dur": 50.362, + "args": { + "External id": 228856,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115457533.021, "dur": 4.790, + "args": { + "External id": 228857,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115457534.478, "dur": 2.829, + "args": { + "External id": 228858,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115457536.096, "dur": 1.071, + "args": { + "External id": 228859,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115457538.862, "dur": 43.272, + "args": { + "External id": 228860,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115457540.091, "dur": 41.516, + "args": { + "External id": 228861,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115457586.494, "dur": 5.802, + "args": { + "External id": 228862,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115457588.464, "dur": 2.713, + "args": { + "External id": 228863,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115457597.626, "dur": 1.423, + "args": { + "External id": 228864,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115457636.904, "dur": 11.962, + "args": { + "External id": 228865,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115457644.530, "dur": 4.087, + "args": { + "External id": 228866,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115457781.538, "dur": 192.013, + "args": { + "External id": 228867,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115457783.865, "dur": 2.933, + "args": { + "External id": 228868,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115457791.045, "dur": 182.049, + "args": { + "External id": 228869,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115457792.737, "dur": 0.432, + "args": { + "External id": 228870,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115457794.584, "dur": 22.761, + "args": { + "External id": 228871,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115457818.922, "dur": 6.074, + "args": { + "External id": 228872,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115457821.396, "dur": 3.229, + "args": { + "External id": 228873,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115457826.080, "dur": 21.528, + "args": { + "External id": 228874,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115457827.189, "dur": 1.458, + "args": { + "External id": 228875,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115457830.398, "dur": 16.955, + "args": { + "External id": 228876,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115457833.323, "dur": 2.688, + "args": { + "External id": 228877,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115457848.896, "dur": 23.664, + "args": { + "External id": 228878,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115457874.307, "dur": 12.540, + "args": { + "External id": 228879,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115457890.202, "dur": 15.864, + "args": { + "External id": 228880,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115457907.615, "dur": 13.125, + "args": { + "External id": 228881,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115457922.678, "dur": 21.559, + "args": { + "External id": 228882,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115457924.607, "dur": 1.593, + "args": { + "External id": 228883,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115457928.747, "dur": 1.308, + "args": { + "External id": 228884,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115457945.968, "dur": 12.522, + "args": { + "External id": 228885,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115457959.610, "dur": 12.255, + "args": { + "External id": 228886,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115457980.127, "dur": 2.213, + "args": { + "External id": 228887,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115457991.215, "dur": 3.715, + "args": { + "External id": 228888,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115457993.705, "dur": 0.385, + "args": { + "External id": 228889,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115458059.971, "dur": 48.085, + "args": { + "External id": 228890,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115458113.327, "dur": 7.522, + "args": { + "External id": 228891,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115458116.202, "dur": 3.547, + "args": { + "External id": 228892,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "58720256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115458122.228, "dur": 23.811, + "args": { + "External id": 228893,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115458150.581, "dur": 5.543, + "args": { + "External id": 228894,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115458152.070, "dur": 3.327, + "args": { + "External id": 228895,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115458154.148, "dur": 1.026, + "args": { + "External id": 228896,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115458158.594, "dur": 41.340, + "args": { + "External id": 228897,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115458159.975, "dur": 38.991, + "args": { + "External id": 228898,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115458202.991, "dur": 14.685, + "args": { + "External id": 228899,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115458222.864, "dur": 23.404, + "args": { + "External id": 228900,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 7699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115458225.541, "dur": 20.379, + "args": { + "External id": 228901,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115458230.289, "dur": 1.119, + "args": { + "External id": 228902,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 7701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115458250.985, "dur": 32.208, + "args": { + "External id": 228903,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[32000, 1024], [], [], [], [], []], "Ev Idx": 7702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115458257.623, "dur": 25.334, + "args": { + "External id": 228904,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], [], []], "Input Dims": [[32000, 1024], [], [], [], [], [], []], "Ev Idx": 7703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115458261.939, "dur": 4.057, + "args": { + "External id": 228905,"Record function id": 0, "Concrete Inputs": ["[32000, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115458267.242, "dur": 15.193, + "args": { + "External id": 228906,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 4183440, + "ts": 667115458295.984, "dur": 5.563, + "args": { + "External id": 228907,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 7706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 4183440, + "ts": 667115458298.401, "dur": 2.908, + "args": { + "External id": 228908,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 7707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 4183440, + "ts": 667115458302.755, "dur": 1.614, + "args": { + "External id": 228909,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 4183440, + "ts": 667115458303.565, "dur": 0.721, + "args": { + "External id": 228910,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115458342.728, "dur": 23.390, + "args": { + "External id": 228911,"Sequence number": 2757940, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 7710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115458368.249, "dur": 13.788, + "args": { + "External id": 228912,"Sequence number": 2757941, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 7711 + } + }, + { + "ph": "s", "id": 16, "pid": 4183440, "tid": 4183440, "ts": 667115458368.249, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115458387.868, "dur": 5.229, + "args": { + "External id": 228913,"Sequence number": 2757942, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 4, 4096], [], [], [], []], "Ev Idx": 7712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115458390.895, "dur": 0.915, + "args": { + "External id": 228914,"Record function id": 0, "Concrete Inputs": ["", "[16, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 7713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183440, "tid": 4183440, + "ts": 667115458396.329, "dur": 6.727, + "args": { + "External id": 228915,"Sequence number": 2757942, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "2"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[16, 4, 4096], [], []], "Ev Idx": 7714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115458400.828, "dur": 0.925, + "args": { + "External id": 228916,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "3"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 7715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115458404.611, "dur": 3.391, + "args": { + "External id": 228917,"Sequence number": 2757942, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], []], "Ev Idx": 7716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115458406.747, "dur": 0.681, + "args": { + "External id": 228918,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "3"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 7717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115458411.937, "dur": 6.209, + "args": { + "External id": 228919,"Sequence number": 2757942, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], []], "Ev Idx": 7718 + } + }, + { + "ph": "s", "id": 15, "pid": 4183440, "tid": 4183440, "ts": 667115458411.937, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115458415.447, "dur": 1.222, + "args": { + "External id": 228920,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "[16777216, 4096, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 7719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115458419.335, "dur": 6.119, + "args": { + "External id": 228921,"Sequence number": 2757943, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], []], "Ev Idx": 7720 + } + }, + { + "ph": "s", "id": 14, "pid": 4183440, "tid": 4183440, "ts": 667115458419.335, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115458423.549, "dur": 1.123, + "args": { + "External id": 228922,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "[16777216, 4096, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 7721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183440, "tid": 4183440, + "ts": 667115458426.414, "dur": 5.207, + "args": { + "External id": 228923,"Sequence number": 2757944, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], []], "Input Dims": [[16, 4096, 4, 1024], [], []], "Ev Idx": 7722 + } + }, + { + "ph": "s", "id": 13, "pid": 4183440, "tid": 4183440, "ts": 667115458426.414, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115458430.207, "dur": 0.538, + "args": { + "External id": 228924,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[16777216, 4096, 1]", "2048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 7723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115458432.757, "dur": 4.976, + "args": { + "External id": 228925,"Sequence number": 2757945, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], [], []], "Ev Idx": 7724 + } + }, + { + "ph": "s", "id": 12, "pid": 4183440, "tid": 4183440, "ts": 667115458432.757, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115458435.928, "dur": 1.087, + "args": { + "External id": 228926,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[16777216, 4096, 1]", "2048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], []], "Ev Idx": 7725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183440, "tid": 4183440, + "ts": 667115458441.497, "dur": 30.002, + "args": { + "External id": 228927,"Sequence number": 2757946, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 7726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 4183440, + "ts": 667115458443.102, "dur": 28.195, + "args": { + "External id": 228928,"Sequence number": 2757946, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 7727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115458445.393, "dur": 6.847, + "args": { + "External id": 228929,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], []], "Ev Idx": 7728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115458448.179, "dur": 3.491, + "args": { + "External id": 228930,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115458453.173, "dur": 17.684, + "args": { + "External id": 228931,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 7730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115458516.506, "dur": 5.873, + "args": { + "External id": 228932,"Sequence number": 2757946, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 7731 + } + }, + { + "ph": "s", "id": 11, "pid": 4183440, "tid": 4183440, "ts": 667115458516.506, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115458525.286, "dur": 3.344, + "args": { + "External id": 228933,"Sequence number": 2757947, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 7732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115458560.935, "dur": 22913.414, + "args": { + "External id": 228934,"Sequence number": 2757947, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536], [32000, 1024], [], [], [], [], []], "Ev Idx": 7733 + } + }, + { + "ph": "s", "id": 10, "pid": 4183440, "tid": 4183440, "ts": 667115458560.935, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183440, "tid": 4183440, + "ts": 667115458575.828, "dur": 34.008, + "args": { + "External id": 228935,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 7734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 4183440, + "ts": 667115458577.123, "dur": 32.534, + "args": { + "External id": 228936,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 7735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115458579.057, "dur": 7.471, + "args": { + "External id": 228937,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 7736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115458581.035, "dur": 4.942, + "args": { + "External id": 228938,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115458587.359, "dur": 21.744, + "args": { + "External id": 228939,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [4096, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 7738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 4183440, "tid": 4183440, + "ts": 667115458625.463, "dur": 61.834, + "args": { + "External id": 228940,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 7739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115458626.760, "dur": 6.331, + "args": { + "External id": 228941,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 7740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115458628.716, "dur": 4.056, + "args": { + "External id": 228942,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 4183440, + "ts": 667115458634.553, "dur": 52.507, + "args": { + "External id": 228943,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 7742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115458636.556, "dur": 49.616, + "args": { + "External id": 228944,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 7743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 4183440, "tid": 4183440, + "ts": 667115458692.676, "dur": 22.675, + "args": { + "External id": 228945,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[32000, 1024], [], [], [], [], []], "Ev Idx": 7744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115458693.562, "dur": 5.555, + "args": { + "External id": 228946,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[32000, 1024], [], [], [], [], []], "Ev Idx": 7745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115458695.382, "dur": 3.503, + "args": { + "External id": 228947,"Record function id": 0, "Concrete Inputs": ["[32000, 1024]", "[1024, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 4183440, + "ts": 667115458699.990, "dur": 15.162, + "args": { + "External id": 228948,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115458700.838, "dur": 13.982, + "args": { + "External id": 228949,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1024, 1], []], "Input Dims": [[32000, 1024], []], "Ev Idx": 7748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 4183440, + "ts": 667115458721.763, "dur": 19.591, + "args": { + "External id": 228950,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 7749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115458723.509, "dur": 4.737, + "args": { + "External id": 228951,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 4183440, + "ts": 667115458728.931, "dur": 12.165, + "args": { + "External id": 228952,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[65536]], "Ev Idx": 7751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115458729.974, "dur": 10.808, + "args": { + "External id": 228953,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 7752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 4183440, "tid": 4183440, + "ts": 667115458746.511, "dur": 23.857, + "args": { + "External id": 228954,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 7753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115458773.455, "dur": 52.961, + "args": { + "External id": 228955,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 7754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115458775.926, "dur": 50.004, + "args": { + "External id": 228956,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115458781.832, "dur": 1.518, + "args": { + "External id": 228957,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 7756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115458785.315, "dur": 23.598, + "args": { + "External id": 228958,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115458786.865, "dur": 21.850, + "args": { + "External id": 228959,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[65536], [], [], [], [], [], []], "Ev Idx": 7758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115458791.462, "dur": 2.616, + "args": { + "External id": 228960,"Record function id": 0, "Concrete Inputs": ["[65536]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115458795.170, "dur": 13.058, + "args": { + "External id": 228961,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[65536], [65536], []], "Ev Idx": 7760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 4183440, "tid": 4183440, + "ts": 667115458830.353, "dur": 17212.798, + "args": { + "External id": 228962,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 7761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 4183440, "tid": 4183440, + "ts": 667115458831.806, "dur": 17210.180, + "args": { + "External id": 228963,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 7762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115476054.505, "dur": 6.890, + "args": { + "External id": 228964,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115476058.700, "dur": 1.018, + "args": { + "External id": 228965,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115476066.758, "dur": 102.817, + "args": { + "External id": 228966,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115476068.606, "dur": 7.140, + "args": { + "External id": 228967,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115476070.935, "dur": 3.814, + "args": { + "External id": 228968,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115476073.381, "dur": 1.072, + "args": { + "External id": 228969,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115476077.532, "dur": 91.320, + "args": { + "External id": 228970,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115476079.182, "dur": 88.800, + "args": { + "External id": 228971,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115476173.195, "dur": 3.965, + "args": { + "External id": 228972,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115476175.364, "dur": 0.667, + "args": { + "External id": 228973,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115476184.438, "dur": 2.411, + "args": { + "External id": 228974,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115476195.733, "dur": 6.806, + "args": { + "External id": 228975,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115476198.192, "dur": 4.042, + "args": { + "External id": 228976,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115476331.129, "dur": 229.694, + "args": { + "External id": 228977,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115476334.334, "dur": 2.466, + "args": { + "External id": 228978,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115476338.207, "dur": 221.872, + "args": { + "External id": 228979,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115476342.927, "dur": 0.493, + "args": { + "External id": 228980,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115476344.687, "dur": 26.538, + "args": { + "External id": 228981,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115476373.584, "dur": 4.544, + "args": { + "External id": 228982,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115476376.555, "dur": 1.057, + "args": { + "External id": 228983,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115476379.252, "dur": 26.826, + "args": { + "External id": 228984,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115476383.251, "dur": 1.461, + "args": { + "External id": 228985,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115476386.173, "dur": 19.645, + "args": { + "External id": 228986,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115476389.998, "dur": 2.632, + "args": { + "External id": 228987,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115476407.697, "dur": 28.382, + "args": { + "External id": 228988,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115476437.942, "dur": 14.476, + "args": { + "External id": 228989,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115476455.240, "dur": 17.268, + "args": { + "External id": 228990,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115476474.164, "dur": 13.676, + "args": { + "External id": 228991,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115476489.972, "dur": 39.868, + "args": { + "External id": 228992,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115476506.219, "dur": 2.332, + "args": { + "External id": 228993,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115476511.807, "dur": 1.001, + "args": { + "External id": 228994,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115476532.238, "dur": 12.981, + "args": { + "External id": 228995,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115476546.595, "dur": 12.642, + "args": { + "External id": 228996,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115476568.483, "dur": 2.424, + "args": { + "External id": 228997,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115476577.967, "dur": 3.897, + "args": { + "External id": 228998,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115476580.295, "dur": 0.699, + "args": { + "External id": 228999,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115476691.148, "dur": 63.488, + "args": { + "External id": 229000,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115476760.951, "dur": 9.687, + "args": { + "External id": 229001,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115476764.218, "dur": 3.358, + "args": { + "External id": 229002,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115476772.360, "dur": 28.028, + "args": { + "External id": 229003,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115476806.573, "dur": 6.942, + "args": { + "External id": 229004,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115476808.400, "dur": 4.000, + "args": { + "External id": 229005,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115476810.967, "dur": 1.164, + "args": { + "External id": 229006,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115476816.740, "dur": 47.109, + "args": { + "External id": 229007,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115476818.311, "dur": 44.909, + "args": { + "External id": 229008,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115476868.453, "dur": 17.874, + "args": { + "External id": 229009,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115476892.934, "dur": 4.083, + "args": { + "External id": 229010,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115476895.298, "dur": 0.783, + "args": { + "External id": 229011,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "8388608"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115476901.962, "dur": 50.070, + "args": { + "External id": 229012,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115476903.180, "dur": 3.629, + "args": { + "External id": 229013,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115476904.012, "dur": 2.202, + "args": { + "External id": 229014,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115476905.529, "dur": 0.539, + "args": { + "External id": 229015,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115476907.820, "dur": 43.812, + "args": { + "External id": 229016,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115476908.471, "dur": 42.607, + "args": { + "External id": 229017,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115476956.437, "dur": 3.704, + "args": { + "External id": 229018,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115476958.400, "dur": 0.645, + "args": { + "External id": 229019,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115476966.511, "dur": 1.804, + "args": { + "External id": 229020,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115476976.954, "dur": 7.031, + "args": { + "External id": 229021,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115476978.974, "dur": 4.670, + "args": { + "External id": 229022,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115477082.151, "dur": 271.480, + "args": { + "External id": 229023,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115477084.386, "dur": 3.954, + "args": { + "External id": 229024,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115477089.930, "dur": 263.277, + "args": { + "External id": 229025,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115477091.376, "dur": 0.396, + "args": { + "External id": 229026,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115477093.184, "dur": 21.866, + "args": { + "External id": 229027,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115477116.828, "dur": 6.137, + "args": { + "External id": 229028,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115477121.632, "dur": 1.023, + "args": { + "External id": 229029,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115477124.006, "dur": 32.663, + "args": { + "External id": 229030,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115477125.149, "dur": 1.374, + "args": { + "External id": 229031,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115477138.081, "dur": 18.343, + "args": { + "External id": 229032,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115477141.118, "dur": 2.734, + "args": { + "External id": 229033,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115477158.182, "dur": 21.177, + "args": { + "External id": 229034,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115477181.074, "dur": 17.050, + "args": { + "External id": 229035,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115477200.646, "dur": 18.124, + "args": { + "External id": 229036,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115477220.242, "dur": 15.444, + "args": { + "External id": 229037,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115477237.827, "dur": 31.103, + "args": { + "External id": 229038,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115477239.975, "dur": 1.312, + "args": { + "External id": 229039,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115477243.468, "dur": 0.998, + "args": { + "External id": 229040,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115477270.671, "dur": 39.076, + "args": { + "External id": 229041,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115477311.250, "dur": 41.222, + "args": { + "External id": 229042,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115477360.040, "dur": 1.673, + "args": { + "External id": 229043,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115477370.660, "dur": 3.028, + "args": { + "External id": 229044,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115477372.499, "dur": 0.387, + "args": { + "External id": 229045,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115477443.703, "dur": 40.495, + "args": { + "External id": 229046,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115477488.870, "dur": 21.930, + "args": { + "External id": 229047,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115477507.836, "dur": 1.059, + "args": { + "External id": 229048,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "8388608"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115477512.427, "dur": 28.799, + "args": { + "External id": 229049,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115477546.538, "dur": 6.267, + "args": { + "External id": 229050,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115477547.974, "dur": 4.058, + "args": { + "External id": 229051,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115477550.269, "dur": 1.565, + "args": { + "External id": 229052,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115477555.986, "dur": 47.230, + "args": { + "External id": 229053,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115477557.031, "dur": 45.500, + "args": { + "External id": 229054,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115477606.729, "dur": 15.494, + "args": { + "External id": 229055,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115477627.942, "dur": 4.454, + "args": { + "External id": 229056,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115477630.723, "dur": 0.841, + "args": { + "External id": 229057,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115477636.420, "dur": 85.115, + "args": { + "External id": 229058,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115477637.500, "dur": 4.498, + "args": { + "External id": 229059,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115477638.415, "dur": 3.025, + "args": { + "External id": 229060,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115477640.238, "dur": 1.064, + "args": { + "External id": 229061,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115477642.717, "dur": 78.201, + "args": { + "External id": 229062,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115477643.846, "dur": 75.910, + "args": { + "External id": 229063,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115477727.952, "dur": 4.765, + "args": { + "External id": 229064,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115477730.552, "dur": 0.844, + "args": { + "External id": 229065,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115477739.259, "dur": 1.696, + "args": { + "External id": 229066,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115477749.247, "dur": 9.178, + "args": { + "External id": 229067,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115477751.661, "dur": 6.453, + "args": { + "External id": 229068,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115477849.385, "dur": 188.049, + "args": { + "External id": 229069,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115477851.584, "dur": 1.913, + "args": { + "External id": 229070,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115477854.845, "dur": 182.023, + "args": { + "External id": 229071,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115477856.619, "dur": 0.308, + "args": { + "External id": 229072,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115477858.603, "dur": 24.913, + "args": { + "External id": 229073,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115477885.095, "dur": 3.608, + "args": { + "External id": 229074,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115477887.492, "dur": 0.951, + "args": { + "External id": 229075,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115477889.816, "dur": 25.835, + "args": { + "External id": 229076,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115477890.996, "dur": 2.151, + "args": { + "External id": 229077,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115477894.325, "dur": 20.996, + "args": { + "External id": 229078,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115477899.442, "dur": 2.540, + "args": { + "External id": 229079,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115477916.909, "dur": 21.640, + "args": { + "External id": 229080,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115477940.206, "dur": 13.908, + "args": { + "External id": 229081,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115477956.847, "dur": 15.171, + "args": { + "External id": 229082,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115477973.406, "dur": 13.093, + "args": { + "External id": 229083,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115477988.498, "dur": 20.389, + "args": { + "External id": 229084,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115477990.194, "dur": 1.167, + "args": { + "External id": 229085,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115477993.279, "dur": 0.914, + "args": { + "External id": 229086,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115478010.593, "dur": 12.414, + "args": { + "External id": 229087,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115478024.014, "dur": 11.928, + "args": { + "External id": 229088,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115478044.020, "dur": 1.639, + "args": { + "External id": 229089,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115478054.549, "dur": 3.287, + "args": { + "External id": 229090,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115478056.611, "dur": 0.503, + "args": { + "External id": 229091,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115478119.028, "dur": 43.664, + "args": { + "External id": 229092,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115478166.865, "dur": 5.344, + "args": { + "External id": 229093,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115478169.919, "dur": 1.315, + "args": { + "External id": 229094,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115478173.535, "dur": 23.594, + "args": { + "External id": 229095,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115478201.332, "dur": 5.159, + "args": { + "External id": 229096,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115478203.101, "dur": 2.762, + "args": { + "External id": 229097,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115478204.821, "dur": 0.823, + "args": { + "External id": 229098,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115478209.008, "dur": 40.640, + "args": { + "External id": 229099,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115478210.120, "dur": 38.829, + "args": { + "External id": 229100,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115478252.705, "dur": 15.579, + "args": { + "External id": 229101,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115478273.306, "dur": 3.674, + "args": { + "External id": 229102,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115478275.522, "dur": 0.706, + "args": { + "External id": 229103,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "25165824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115478280.757, "dur": 47.344, + "args": { + "External id": 229104,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115478281.844, "dur": 5.829, + "args": { + "External id": 229105,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115478282.720, "dur": 4.372, + "args": { + "External id": 229106,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115478284.325, "dur": 2.535, + "args": { + "External id": 229107,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115478288.390, "dur": 39.287, + "args": { + "External id": 229108,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115478289.260, "dur": 37.792, + "args": { + "External id": 229109,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115478331.428, "dur": 3.523, + "args": { + "External id": 229110,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115478333.397, "dur": 0.491, + "args": { + "External id": 229111,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115478339.821, "dur": 1.430, + "args": { + "External id": 229112,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115478347.818, "dur": 6.042, + "args": { + "External id": 229113,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115478349.762, "dur": 3.830, + "args": { + "External id": 229114,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115478428.734, "dur": 181.304, + "args": { + "External id": 229115,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115478430.951, "dur": 1.995, + "args": { + "External id": 229116,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115478434.423, "dur": 175.125, + "args": { + "External id": 229117,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115478435.475, "dur": 0.528, + "args": { + "External id": 229118,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115478439.862, "dur": 17.074, + "args": { + "External id": 229119,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115478458.455, "dur": 2.820, + "args": { + "External id": 229120,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115478460.142, "dur": 0.947, + "args": { + "External id": 229121,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115478462.041, "dur": 19.918, + "args": { + "External id": 229122,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115478463.012, "dur": 3.423, + "args": { + "External id": 229123,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115478467.748, "dur": 13.923, + "args": { + "External id": 229124,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115478469.813, "dur": 1.947, + "args": { + "External id": 229125,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115478483.174, "dur": 36.874, + "args": { + "External id": 229126,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115478522.187, "dur": 12.326, + "args": { + "External id": 229127,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115478537.296, "dur": 12.989, + "args": { + "External id": 229128,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115478551.725, "dur": 11.559, + "args": { + "External id": 229129,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115478565.300, "dur": 19.123, + "args": { + "External id": 229130,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115478566.973, "dur": 1.752, + "args": { + "External id": 229131,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115478571.101, "dur": 1.176, + "args": { + "External id": 229132,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115478585.962, "dur": 10.927, + "args": { + "External id": 229133,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115478598.036, "dur": 10.580, + "args": { + "External id": 229134,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115478616.389, "dur": 1.852, + "args": { + "External id": 229135,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115478627.789, "dur": 3.536, + "args": { + "External id": 229136,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115478629.914, "dur": 0.577, + "args": { + "External id": 229137,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115478732.883, "dur": 47.721, + "args": { + "External id": 229138,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115478785.975, "dur": 5.732, + "args": { + "External id": 229139,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115478789.234, "dur": 1.016, + "args": { + "External id": 229140,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "25165824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115478793.266, "dur": 22.343, + "args": { + "External id": 229141,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115478820.729, "dur": 5.473, + "args": { + "External id": 229142,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115478821.996, "dur": 3.361, + "args": { + "External id": 229143,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115478824.159, "dur": 0.956, + "args": { + "External id": 229144,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115478829.141, "dur": 40.284, + "args": { + "External id": 229145,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115478830.132, "dur": 38.562, + "args": { + "External id": 229146,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115478872.864, "dur": 13.886, + "args": { + "External id": 229147,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115478892.435, "dur": 3.546, + "args": { + "External id": 229148,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115478894.628, "dur": 0.565, + "args": { + "External id": 229149,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115478899.940, "dur": 61.332, + "args": { + "External id": 229150,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115478900.927, "dur": 6.061, + "args": { + "External id": 229151,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115478901.726, "dur": 4.630, + "args": { + "External id": 229152,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115478905.504, "dur": 0.740, + "args": { + "External id": 229153,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115478920.021, "dur": 40.819, + "args": { + "External id": 229154,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115478921.247, "dur": 38.945, + "args": { + "External id": 229155,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115478965.679, "dur": 3.777, + "args": { + "External id": 229156,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115478967.545, "dur": 0.813, + "args": { + "External id": 229157,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115478975.087, "dur": 1.633, + "args": { + "External id": 229158,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 7957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115478984.343, "dur": 5.663, + "args": { + "External id": 229159,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 7958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115478986.263, "dur": 3.481, + "args": { + "External id": 229160,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115479070.926, "dur": 167.209, + "args": { + "External id": 229161,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115479075.164, "dur": 2.227, + "args": { + "External id": 229162,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115479078.643, "dur": 159.019, + "args": { + "External id": 229163,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 7962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115479079.941, "dur": 0.559, + "args": { + "External id": 229164,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115479081.913, "dur": 19.099, + "args": { + "External id": 229165,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 7964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115479102.652, "dur": 5.112, + "args": { + "External id": 229166,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 7965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115479106.899, "dur": 0.660, + "args": { + "External id": 229167,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 7966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115479108.519, "dur": 21.857, + "args": { + "External id": 229168,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115479109.697, "dur": 2.489, + "args": { + "External id": 229169,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115479113.474, "dur": 16.586, + "args": { + "External id": 229170,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 7969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115479116.030, "dur": 2.281, + "args": { + "External id": 229171,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115479132.087, "dur": 18.890, + "args": { + "External id": 229172,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115479152.317, "dur": 14.334, + "args": { + "External id": 229173,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115479168.888, "dur": 12.061, + "args": { + "External id": 229174,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 7973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115479182.375, "dur": 10.960, + "args": { + "External id": 229175,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 7974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115479195.021, "dur": 18.867, + "args": { + "External id": 229176,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 7975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115479197.215, "dur": 1.294, + "args": { + "External id": 229177,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 7976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115479200.773, "dur": 0.880, + "args": { + "External id": 229178,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 7977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115479215.220, "dur": 10.359, + "args": { + "External id": 229179,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 7978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115479226.856, "dur": 9.940, + "args": { + "External id": 229180,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 7979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115479243.805, "dur": 1.567, + "args": { + "External id": 229181,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 7980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115479253.257, "dur": 3.519, + "args": { + "External id": 229182,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 7981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115479255.524, "dur": 0.459, + "args": { + "External id": 229183,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 7982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115479311.688, "dur": 37.010, + "args": { + "External id": 229184,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 7983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115479353.050, "dur": 4.916, + "args": { + "External id": 229185,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115479355.812, "dur": 1.071, + "args": { + "External id": 229186,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115479359.101, "dur": 21.019, + "args": { + "External id": 229187,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 7986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115479384.005, "dur": 5.210, + "args": { + "External id": 229188,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 7987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115479385.119, "dur": 3.364, + "args": { + "External id": 229189,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 7988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115479386.876, "dur": 1.392, + "args": { + "External id": 229190,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 7989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115479391.772, "dur": 37.703, + "args": { + "External id": 229191,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115479392.745, "dur": 36.121, + "args": { + "External id": 229192,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 7991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115479432.353, "dur": 12.887, + "args": { + "External id": 229193,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 7992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115479449.756, "dur": 4.051, + "args": { + "External id": 229194,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 7993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115479452.349, "dur": 0.692, + "args": { + "External id": 229195,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "41943040"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 7994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115479457.410, "dur": 63.596, + "args": { + "External id": 229196,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 7995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115479458.369, "dur": 3.700, + "args": { + "External id": 229197,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 7996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115479458.965, "dur": 2.604, + "args": { + "External id": 229198,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 7997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115479460.649, "dur": 0.696, + "args": { + "External id": 229199,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 7998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115479462.723, "dur": 57.762, + "args": { + "External id": 229200,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 7999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115479463.566, "dur": 55.782, + "args": { + "External id": 229201,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115479526.700, "dur": 4.573, + "args": { + "External id": 229202,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115479529.175, "dur": 0.864, + "args": { + "External id": 229203,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115479537.089, "dur": 1.549, + "args": { + "External id": 229204,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115479546.062, "dur": 8.563, + "args": { + "External id": 229205,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115479547.954, "dur": 6.332, + "args": { + "External id": 229206,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115479634.944, "dur": 214.658, + "args": { + "External id": 229207,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115479637.081, "dur": 2.007, + "args": { + "External id": 229208,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115479640.608, "dur": 208.363, + "args": { + "External id": 229209,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115479642.431, "dur": 0.450, + "args": { + "External id": 229210,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115479644.027, "dur": 63.306, + "args": { + "External id": 229211,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115479709.853, "dur": 4.220, + "args": { + "External id": 229212,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115479712.553, "dur": 1.128, + "args": { + "External id": 229213,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115479715.300, "dur": 23.929, + "args": { + "External id": 229214,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115479716.356, "dur": 2.290, + "args": { + "External id": 229215,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115479719.800, "dur": 19.119, + "args": { + "External id": 229216,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115479725.464, "dur": 2.479, + "args": { + "External id": 229217,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115479740.807, "dur": 20.055, + "args": { + "External id": 229218,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115479762.118, "dur": 12.187, + "args": { + "External id": 229219,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115479776.919, "dur": 13.374, + "args": { + "External id": 229220,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115479791.460, "dur": 12.052, + "args": { + "External id": 229221,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115479805.293, "dur": 18.410, + "args": { + "External id": 229222,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115479807.125, "dur": 1.367, + "args": { + "External id": 229223,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115479810.879, "dur": 1.094, + "args": { + "External id": 229224,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115479825.331, "dur": 10.855, + "args": { + "External id": 229225,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115479837.341, "dur": 10.653, + "args": { + "External id": 229226,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115479857.268, "dur": 1.914, + "args": { + "External id": 229227,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115479867.377, "dur": 3.635, + "args": { + "External id": 229228,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115479869.897, "dur": 0.300, + "args": { + "External id": 229229,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115479941.174, "dur": 48.517, + "args": { + "External id": 229230,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 8029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115479994.218, "dur": 5.486, + "args": { + "External id": 229231,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115479997.368, "dur": 1.250, + "args": { + "External id": 229232,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "41943040"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115480000.977, "dur": 23.348, + "args": { + "External id": 229233,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 8032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115480028.950, "dur": 6.239, + "args": { + "External id": 229234,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115480030.594, "dur": 3.977, + "args": { + "External id": 229235,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115480033.086, "dur": 1.241, + "args": { + "External id": 229236,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115480037.888, "dur": 41.139, + "args": { + "External id": 229237,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115480038.962, "dur": 39.359, + "args": { + "External id": 229238,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115480082.587, "dur": 13.608, + "args": { + "External id": 229239,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 8038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115480101.693, "dur": 3.814, + "args": { + "External id": 229240,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115480103.996, "dur": 0.677, + "args": { + "External id": 229241,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115480109.397, "dur": 56.109, + "args": { + "External id": 229242,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 8041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115480110.561, "dur": 5.875, + "args": { + "External id": 229243,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 8042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115480111.260, "dur": 4.600, + "args": { + "External id": 229244,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 8043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115480112.798, "dur": 2.884, + "args": { + "External id": 229245,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 8044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115480117.209, "dur": 47.906, + "args": { + "External id": 229246,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115480117.956, "dur": 46.513, + "args": { + "External id": 229247,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115480169.296, "dur": 3.713, + "args": { + "External id": 229248,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115480171.130, "dur": 0.760, + "args": { + "External id": 229249,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115480177.692, "dur": 1.470, + "args": { + "External id": 229250,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115480186.320, "dur": 5.590, + "args": { + "External id": 229251,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115480188.082, "dur": 3.485, + "args": { + "External id": 229252,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115480268.632, "dur": 211.468, + "args": { + "External id": 229253,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115480270.652, "dur": 2.273, + "args": { + "External id": 229254,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115480274.345, "dur": 205.170, + "args": { + "External id": 229255,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115480275.508, "dur": 0.437, + "args": { + "External id": 229256,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115480279.508, "dur": 23.549, + "args": { + "External id": 229257,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115480304.691, "dur": 2.759, + "args": { + "External id": 229258,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115480306.559, "dur": 0.673, + "args": { + "External id": 229259,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115480308.155, "dur": 32.481, + "args": { + "External id": 229260,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115480309.800, "dur": 3.741, + "args": { + "External id": 229261,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115480314.752, "dur": 25.597, + "args": { + "External id": 229262,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115480317.423, "dur": 1.992, + "args": { + "External id": 229263,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115480342.231, "dur": 26.155, + "args": { + "External id": 229264,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115480369.590, "dur": 28.684, + "args": { + "External id": 229265,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115480400.556, "dur": 16.858, + "args": { + "External id": 229266,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115480418.570, "dur": 12.214, + "args": { + "External id": 229267,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115480432.612, "dur": 19.556, + "args": { + "External id": 229268,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115480434.353, "dur": 1.621, + "args": { + "External id": 229269,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115480437.937, "dur": 0.714, + "args": { + "External id": 229270,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115480453.554, "dur": 12.670, + "args": { + "External id": 229271,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115480467.358, "dur": 10.970, + "args": { + "External id": 229272,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115480485.865, "dur": 1.413, + "args": { + "External id": 229273,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115480517.614, "dur": 4.369, + "args": { + "External id": 229274,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115480520.131, "dur": 0.729, + "args": { + "External id": 229275,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115480588.527, "dur": 46.048, + "args": { + "External id": 229276,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 8075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115480684.353, "dur": 7.388, + "args": { + "External id": 229277,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115480688.787, "dur": 1.240, + "args": { + "External id": 229278,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115480693.073, "dur": 28.068, + "args": { + "External id": 229279,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 8078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115480726.788, "dur": 7.732, + "args": { + "External id": 229280,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115480728.471, "dur": 5.344, + "args": { + "External id": 229281,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115480730.597, "dur": 2.956, + "args": { + "External id": 229282,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115480737.483, "dur": 45.858, + "args": { + "External id": 229283,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115480738.808, "dur": 43.894, + "args": { + "External id": 229284,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115480787.232, "dur": 16.057, + "args": { + "External id": 229285,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 8084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115480809.277, "dur": 4.328, + "args": { + "External id": 229286,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115480811.935, "dur": 0.905, + "args": { + "External id": 229287,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "58720256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115480817.416, "dur": 47.886, + "args": { + "External id": 229288,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 8087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115480818.269, "dur": 3.905, + "args": { + "External id": 229289,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 8088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115480819.292, "dur": 2.341, + "args": { + "External id": 229290,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 8089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115480820.609, "dur": 0.891, + "args": { + "External id": 229291,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 8090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115480822.788, "dur": 42.074, + "args": { + "External id": 229292,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115480823.646, "dur": 40.465, + "args": { + "External id": 229293,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115480868.949, "dur": 3.843, + "args": { + "External id": 229294,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115480870.986, "dur": 0.786, + "args": { + "External id": 229295,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115480878.924, "dur": 1.755, + "args": { + "External id": 229296,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115480888.346, "dur": 7.516, + "args": { + "External id": 229297,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115480890.471, "dur": 5.024, + "args": { + "External id": 229298,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115480977.798, "dur": 186.742, + "args": { + "External id": 229299,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115480979.757, "dur": 2.182, + "args": { + "External id": 229300,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115480985.693, "dur": 178.331, + "args": { + "External id": 229301,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115480986.977, "dur": 0.388, + "args": { + "External id": 229302,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115480988.975, "dur": 21.116, + "args": { + "External id": 229303,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115481011.466, "dur": 5.998, + "args": { + "External id": 229304,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115481013.648, "dur": 3.523, + "args": { + "External id": 229305,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115481018.411, "dur": 20.363, + "args": { + "External id": 229306,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115481019.596, "dur": 1.319, + "args": { + "External id": 229307,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115481022.053, "dur": 16.464, + "args": { + "External id": 229308,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115481024.671, "dur": 2.252, + "args": { + "External id": 229309,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115481040.166, "dur": 19.278, + "args": { + "External id": 229310,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115481060.790, "dur": 12.381, + "args": { + "External id": 229311,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115481075.806, "dur": 17.548, + "args": { + "External id": 229312,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115481094.538, "dur": 16.929, + "args": { + "External id": 229313,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115481113.297, "dur": 23.647, + "args": { + "External id": 229314,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115481115.185, "dur": 1.460, + "args": { + "External id": 229315,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115481118.768, "dur": 0.558, + "args": { + "External id": 229316,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115481138.567, "dur": 12.209, + "args": { + "External id": 229317,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115481151.901, "dur": 10.939, + "args": { + "External id": 229318,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115481169.659, "dur": 1.658, + "args": { + "External id": 229319,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115481179.723, "dur": 2.986, + "args": { + "External id": 229320,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115481181.507, "dur": 0.467, + "args": { + "External id": 229321,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115481240.695, "dur": 37.011, + "args": { + "External id": 229322,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 8121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115481282.108, "dur": 6.247, + "args": { + "External id": 229323,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115481284.429, "dur": 2.866, + "args": { + "External id": 229324,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "58720256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115481289.749, "dur": 19.290, + "args": { + "External id": 229325,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 8124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115481312.991, "dur": 5.344, + "args": { + "External id": 229326,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115481314.510, "dur": 3.195, + "args": { + "External id": 229327,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115481316.260, "dur": 1.217, + "args": { + "External id": 229328,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115481320.494, "dur": 37.946, + "args": { + "External id": 229329,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115481322.015, "dur": 35.629, + "args": { + "External id": 229330,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115481361.439, "dur": 13.181, + "args": { + "External id": 229331,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 8130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115481379.267, "dur": 20.970, + "args": { + "External id": 229332,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 8131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115481381.534, "dur": 18.352, + "args": { + "External id": 229333,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115481386.359, "dur": 1.021, + "args": { + "External id": 229334,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115481405.071, "dur": 25.674, + "args": { + "External id": 229335,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[32000, 1024], [], [], [], [], []], "Ev Idx": 8134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115481406.688, "dur": 23.855, + "args": { + "External id": 229336,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], [], []], "Input Dims": [[32000, 1024], [], [], [], [], [], []], "Ev Idx": 8135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115481411.056, "dur": 4.201, + "args": { + "External id": 229337,"Record function id": 0, "Concrete Inputs": ["[32000, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115481416.771, "dur": 13.213, + "args": { + "External id": 229338,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 8137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 4183440, + "ts": 667115481441.654, "dur": 5.254, + "args": { + "External id": 229339,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 8138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 4183440, + "ts": 667115481443.915, "dur": 2.773, + "args": { + "External id": 229340,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 8139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 4183440, + "ts": 667115481447.997, "dur": 1.415, + "args": { + "External id": 229341,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 8140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 4183440, + "ts": 667115481448.773, "dur": 0.572, + "args": { + "External id": 229342,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 8141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115481511.024, "dur": 25.895, + "args": { + "External id": 229343,"Sequence number": 2757948, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 8142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115481539.329, "dur": 12.791, + "args": { + "External id": 229344,"Sequence number": 2757949, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 8143 + } + }, + { + "ph": "s", "id": 9, "pid": 4183440, "tid": 4183440, "ts": 667115481539.329, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115481558.496, "dur": 6.742, + "args": { + "External id": 229345,"Sequence number": 2757950, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 4, 4096], [], [], [], []], "Ev Idx": 8144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115481562.373, "dur": 1.270, + "args": { + "External id": 229346,"Record function id": 0, "Concrete Inputs": ["", "[16, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 8145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183440, "tid": 4183440, + "ts": 667115481567.853, "dur": 6.826, + "args": { + "External id": 229347,"Sequence number": 2757950, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "3"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[16, 4, 4096], [], []], "Ev Idx": 8146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115481572.488, "dur": 0.814, + "args": { + "External id": 229348,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "4"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 8147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115481576.171, "dur": 3.351, + "args": { + "External id": 229349,"Sequence number": 2757950, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], []], "Ev Idx": 8148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115481577.931, "dur": 1.044, + "args": { + "External id": 229350,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "4"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 8149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115481583.431, "dur": 6.657, + "args": { + "External id": 229351,"Sequence number": 2757950, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], []], "Ev Idx": 8150 + } + }, + { + "ph": "s", "id": 8, "pid": 4183440, "tid": 4183440, "ts": 667115481583.431, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115481587.471, "dur": 1.159, + "args": { + "External id": 229352,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "[16777216, 4096, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 8151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115481591.184, "dur": 5.434, + "args": { + "External id": 229353,"Sequence number": 2757951, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], [], []], "Ev Idx": 8152 + } + }, + { + "ph": "s", "id": 7, "pid": 4183440, "tid": 4183440, "ts": 667115481591.184, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115481594.982, "dur": 0.814, + "args": { + "External id": 229354,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 1024]", "[16777216, 4096, 1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 8153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 4183440, "tid": 4183440, + "ts": 667115481597.563, "dur": 5.126, + "args": { + "External id": 229355,"Sequence number": 2757952, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], []], "Input Dims": [[16, 4096, 4, 1024], [], []], "Ev Idx": 8154 + } + }, + { + "ph": "s", "id": 6, "pid": 4183440, "tid": 4183440, "ts": 667115481597.563, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115481601.007, "dur": 0.785, + "args": { + "External id": 229356,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[16777216, 4096, 1]", "3072"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1024, 1], [], [], []], "Input Dims": [[16, 4096, 4, 1024], [], [], []], "Ev Idx": 8155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115481603.656, "dur": 4.304, + "args": { + "External id": 229357,"Sequence number": 2757953, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], [], []], "Ev Idx": 8156 + } + }, + { + "ph": "s", "id": 5, "pid": 4183440, "tid": 4183440, "ts": 667115481603.656, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115481606.300, "dur": 0.790, + "args": { + "External id": 229358,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1024]", "[16777216, 4096, 1]", "3072"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[16, 4096, 1024], [], [], []], "Ev Idx": 8157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183440, "tid": 4183440, + "ts": 667115481611.682, "dur": 28.509, + "args": { + "External id": 229359,"Sequence number": 2757954, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 8158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 4183440, + "ts": 667115481612.957, "dur": 27.043, + "args": { + "External id": 229360,"Sequence number": 2757954, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 8159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115481615.907, "dur": 6.882, + "args": { + "External id": 229361,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], []], "Ev Idx": 8160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115481618.314, "dur": 3.855, + "args": { + "External id": 229362,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115481623.742, "dur": 15.678, + "args": { + "External id": 229363,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 8162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115481703.170, "dur": 5.933, + "args": { + "External id": 229364,"Sequence number": 2757954, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[16, 4096, 1024], []], "Ev Idx": 8163 + } + }, + { + "ph": "s", "id": 4, "pid": 4183440, "tid": 4183440, "ts": 667115481703.170, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115481711.967, "dur": 3.023, + "args": { + "External id": 229365,"Sequence number": 2757955, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 8164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 4183440, "tid": 4183440, + "ts": 667115481746.954, "dur": 23594.547, + "args": { + "External id": 229366,"Sequence number": 2757955, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [65536], [32000, 1024], [], [], [], [], []], "Ev Idx": 8165 + } + }, + { + "ph": "s", "id": 3, "pid": 4183440, "tid": 4183440, "ts": 667115481746.954, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 4183440, "tid": 4183440, + "ts": 667115481762.340, "dur": 29.946, + "args": { + "External id": 229367,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 8166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 4183440, + "ts": 667115481763.200, "dur": 28.905, + "args": { + "External id": 229368,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 8167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115481764.775, "dur": 6.511, + "args": { + "External id": 229369,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 8168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115481766.687, "dur": 4.207, + "args": { + "External id": 229370,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115481772.334, "dur": 19.345, + "args": { + "External id": 229371,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [4096, 1], []], "Input Dims": [[65536, 1024], [65536, 1024], []], "Ev Idx": 8170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 4183440, "tid": 4183440, + "ts": 667115481807.961, "dur": 24.320, + "args": { + "External id": 229372,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 8171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115481809.194, "dur": 6.209, + "args": { + "External id": 229373,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], [], []], "Ev Idx": 8172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115481811.100, "dur": 4.015, + "args": { + "External id": 229374,"Record function id": 0, "Concrete Inputs": ["[65536, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 4183440, + "ts": 667115481816.680, "dur": 15.376, + "args": { + "External id": 229375,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 8174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115481818.431, "dur": 13.188, + "args": { + "External id": 229376,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], []], "Input Dims": [[65536, 1024], []], "Ev Idx": 8175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 4183440, "tid": 4183440, + "ts": 667115481869.846, "dur": 26.725, + "args": { + "External id": 229377,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[32000, 1024], [], [], [], [], []], "Ev Idx": 8176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115481870.571, "dur": 12.537, + "args": { + "External id": 229378,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[32000, 1024], [], [], [], [], []], "Ev Idx": 8177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115481879.924, "dur": 2.914, + "args": { + "External id": 229379,"Record function id": 0, "Concrete Inputs": ["[32000, 1024]", "[1024, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 4183440, + "ts": 667115481883.647, "dur": 12.727, + "args": { + "External id": 229380,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 8179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115481884.080, "dur": 11.940, + "args": { + "External id": 229381,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1024, 1], []], "Input Dims": [[32000, 1024], []], "Ev Idx": 8180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 4183440, + "ts": 667115481902.594, "dur": 20.809, + "args": { + "External id": 229382,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 8181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115481904.243, "dur": 4.429, + "args": { + "External id": 229383,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 4183440, + "ts": 667115481909.246, "dur": 13.902, + "args": { + "External id": 229384,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[65536]], "Ev Idx": 8183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115481909.804, "dur": 12.840, + "args": { + "External id": 229385,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 8184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 4183440, "tid": 4183440, + "ts": 667115481928.654, "dur": 20.381, + "args": { + "External id": 229386,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 8185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115481952.288, "dur": 46.341, + "args": { + "External id": 229387,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 8186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115481953.960, "dur": 44.105, + "args": { + "External id": 229388,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115481958.392, "dur": 0.883, + "args": { + "External id": 229389,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115481960.940, "dur": 22.781, + "args": { + "External id": 229390,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115481962.382, "dur": 21.100, + "args": { + "External id": 229391,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[65536], [], [], [], [], [], []], "Ev Idx": 8190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115481966.303, "dur": 2.435, + "args": { + "External id": 229392,"Record function id": 0, "Concrete Inputs": ["[65536]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115481969.573, "dur": 13.579, + "args": { + "External id": 229393,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[65536], [65536], []], "Ev Idx": 8192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 4183440, "tid": 4183440, + "ts": 667115482002.776, "dur": 17896.015, + "args": { + "External id": 229394,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 8193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 4183440, "tid": 4183440, + "ts": 667115482004.054, "dur": 17893.587, + "args": { + "External id": 229395,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 8194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115499908.882, "dur": 6.764, + "args": { + "External id": 229396,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115499912.704, "dur": 1.169, + "args": { + "External id": 229397,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115499920.850, "dur": 106.748, + "args": { + "External id": 229398,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 8197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115499922.810, "dur": 6.140, + "args": { + "External id": 229399,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 8198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115499924.758, "dur": 3.294, + "args": { + "External id": 229400,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 8199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115499926.721, "dur": 1.040, + "args": { + "External id": 229401,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 8200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115499930.185, "dur": 96.505, + "args": { + "External id": 229402,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115499931.847, "dur": 93.778, + "args": { + "External id": 229403,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115500030.907, "dur": 4.454, + "args": { + "External id": 229404,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115500033.046, "dur": 0.916, + "args": { + "External id": 229405,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115500042.241, "dur": 2.566, + "args": { + "External id": 229406,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115500058.729, "dur": 6.685, + "args": { + "External id": 229407,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115500061.031, "dur": 4.129, + "args": { + "External id": 229408,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115500197.997, "dur": 190.513, + "args": { + "External id": 229409,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115500202.761, "dur": 2.267, + "args": { + "External id": 229410,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115500206.508, "dur": 181.494, + "args": { + "External id": 229411,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115500208.456, "dur": 0.607, + "args": { + "External id": 229412,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115500210.830, "dur": 23.707, + "args": { + "External id": 229413,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115500236.329, "dur": 5.992, + "args": { + "External id": 229414,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115500240.999, "dur": 1.009, + "args": { + "External id": 229415,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115500243.535, "dur": 23.848, + "args": { + "External id": 229416,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115500244.916, "dur": 1.678, + "args": { + "External id": 229417,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115500248.045, "dur": 19.077, + "args": { + "External id": 229418,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115500251.591, "dur": 3.237, + "args": { + "External id": 229419,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115500269.087, "dur": 23.706, + "args": { + "External id": 229420,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115500294.668, "dur": 14.184, + "args": { + "External id": 229421,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115500311.961, "dur": 14.137, + "args": { + "External id": 229422,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115500327.758, "dur": 12.289, + "args": { + "External id": 229423,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115500342.281, "dur": 20.178, + "args": { + "External id": 229424,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115500344.600, "dur": 1.744, + "args": { + "External id": 229425,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115500348.745, "dur": 0.920, + "args": { + "External id": 229426,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115500364.053, "dur": 11.376, + "args": { + "External id": 229427,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115500376.966, "dur": 10.293, + "args": { + "External id": 229428,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115500394.688, "dur": 2.162, + "args": { + "External id": 229429,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115500402.755, "dur": 4.561, + "args": { + "External id": 229430,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115500405.436, "dur": 0.772, + "args": { + "External id": 229431,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115500478.354, "dur": 71.335, + "args": { + "External id": 229432,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 8231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115500556.396, "dur": 14.324, + "args": { + "External id": 229433,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115500565.276, "dur": 2.137, + "args": { + "External id": 229434,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115500572.433, "dur": 26.408, + "args": { + "External id": 229435,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 8234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115500605.225, "dur": 8.558, + "args": { + "External id": 229436,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115500607.274, "dur": 5.618, + "args": { + "External id": 229437,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115500609.381, "dur": 3.197, + "args": { + "External id": 229438,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115500617.265, "dur": 82.293, + "args": { + "External id": 229439,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115500618.646, "dur": 79.528, + "args": { + "External id": 229440,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115500705.770, "dur": 16.992, + "args": { + "External id": 229441,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 8240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115500729.866, "dur": 5.130, + "args": { + "External id": 229442,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115500732.707, "dur": 1.093, + "args": { + "External id": 229443,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "8388608"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115500739.805, "dur": 53.914, + "args": { + "External id": 229444,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 8243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115500741.009, "dur": 4.391, + "args": { + "External id": 229445,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 8244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115500742.092, "dur": 2.716, + "args": { + "External id": 229446,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 8245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115500743.984, "dur": 0.673, + "args": { + "External id": 229447,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 8246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115500746.192, "dur": 47.164, + "args": { + "External id": 229448,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115500746.930, "dur": 45.692, + "args": { + "External id": 229449,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115500797.655, "dur": 4.151, + "args": { + "External id": 229450,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115500799.749, "dur": 0.814, + "args": { + "External id": 229451,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115500808.339, "dur": 1.965, + "args": { + "External id": 229452,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115500819.408, "dur": 7.393, + "args": { + "External id": 229453,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115500821.881, "dur": 4.634, + "args": { + "External id": 229454,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115500928.947, "dur": 221.833, + "args": { + "External id": 229455,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115500931.158, "dur": 2.503, + "args": { + "External id": 229456,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115500937.716, "dur": 212.556, + "args": { + "External id": 229457,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115500939.336, "dur": 0.554, + "args": { + "External id": 229458,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115500941.262, "dur": 20.466, + "args": { + "External id": 229459,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115500963.265, "dur": 5.885, + "args": { + "External id": 229460,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115500965.682, "dur": 3.153, + "args": { + "External id": 229461,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115500970.051, "dur": 21.164, + "args": { + "External id": 229462,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115500971.488, "dur": 1.580, + "args": { + "External id": 229463,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115500974.321, "dur": 16.639, + "args": { + "External id": 229464,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115500977.341, "dur": 2.699, + "args": { + "External id": 229465,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115500992.822, "dur": 20.310, + "args": { + "External id": 229466,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115501014.963, "dur": 12.122, + "args": { + "External id": 229467,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115501029.669, "dur": 13.237, + "args": { + "External id": 229468,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115501044.365, "dur": 12.112, + "args": { + "External id": 229469,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115501058.388, "dur": 25.743, + "args": { + "External id": 229470,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115501060.886, "dur": 2.541, + "args": { + "External id": 229471,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115501065.708, "dur": 3.065, + "args": { + "External id": 229472,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115501085.504, "dur": 18.134, + "args": { + "External id": 229473,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115501105.015, "dur": 44.455, + "args": { + "External id": 229474,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115501157.395, "dur": 2.035, + "args": { + "External id": 229475,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115501168.079, "dur": 3.685, + "args": { + "External id": 229476,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115501170.220, "dur": 0.486, + "args": { + "External id": 229477,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115501239.096, "dur": 43.094, + "args": { + "External id": 229478,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 8277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115501287.371, "dur": 5.370, + "args": { + "External id": 229479,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115501290.367, "dur": 0.958, + "args": { + "External id": 229480,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "8388608"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115501294.257, "dur": 22.131, + "args": { + "External id": 229481,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 8280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115501329.114, "dur": 8.778, + "args": { + "External id": 229482,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115501331.257, "dur": 5.942, + "args": { + "External id": 229483,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115501333.438, "dur": 3.463, + "args": { + "External id": 229484,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115501340.497, "dur": 44.468, + "args": { + "External id": 229485,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115501341.851, "dur": 42.236, + "args": { + "External id": 229486,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115501388.321, "dur": 13.557, + "args": { + "External id": 229487,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 8286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115501407.202, "dur": 4.194, + "args": { + "External id": 229488,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115501409.921, "dur": 0.629, + "args": { + "External id": 229489,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115501415.601, "dur": 47.743, + "args": { + "External id": 229490,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 8289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115501416.537, "dur": 4.368, + "args": { + "External id": 229491,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 8290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115501417.362, "dur": 2.988, + "args": { + "External id": 229492,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 8291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115501419.331, "dur": 0.882, + "args": { + "External id": 229493,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 8292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115501421.498, "dur": 41.429, + "args": { + "External id": 229494,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115501422.535, "dur": 39.697, + "args": { + "External id": 229495,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115501467.171, "dur": 4.281, + "args": { + "External id": 229496,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115501469.409, "dur": 0.811, + "args": { + "External id": 229497,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115501476.711, "dur": 1.499, + "args": { + "External id": 229498,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115501485.380, "dur": 22.631, + "args": { + "External id": 229499,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115501487.698, "dur": 19.708, + "args": { + "External id": 229500,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115501601.072, "dur": 228.753, + "args": { + "External id": 229501,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115501603.409, "dur": 2.641, + "args": { + "External id": 229502,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115501609.668, "dur": 219.545, + "args": { + "External id": 229503,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115501611.186, "dur": 0.421, + "args": { + "External id": 229504,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115501613.121, "dur": 22.527, + "args": { + "External id": 229505,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115501637.109, "dur": 4.933, + "args": { + "External id": 229506,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115501639.307, "dur": 2.442, + "args": { + "External id": 229507,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115501642.889, "dur": 57.351, + "args": { + "External id": 229508,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115501643.918, "dur": 1.435, + "args": { + "External id": 229509,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115501646.541, "dur": 53.333, + "args": { + "External id": 229510,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115501649.384, "dur": 34.611, + "args": { + "External id": 229511,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115501705.072, "dur": 22.323, + "args": { + "External id": 229512,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115501728.837, "dur": 17.869, + "args": { + "External id": 229513,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115501749.199, "dur": 13.530, + "args": { + "External id": 229514,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115501764.070, "dur": 13.807, + "args": { + "External id": 229515,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115501779.663, "dur": 21.664, + "args": { + "External id": 229516,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115501781.736, "dur": 2.031, + "args": { + "External id": 229517,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115501786.097, "dur": 0.823, + "args": { + "External id": 229518,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115501802.975, "dur": 13.116, + "args": { + "External id": 229519,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115501817.407, "dur": 10.731, + "args": { + "External id": 229520,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115501837.369, "dur": 2.498, + "args": { + "External id": 229521,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115501850.385, "dur": 3.762, + "args": { + "External id": 229522,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115501852.397, "dur": 0.705, + "args": { + "External id": 229523,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115501924.792, "dur": 48.867, + "args": { + "External id": 229524,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 8323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115501978.824, "dur": 4.627, + "args": { + "External id": 229525,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115501981.262, "dur": 1.239, + "args": { + "External id": 229526,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115501984.770, "dur": 23.648, + "args": { + "External id": 229527,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 8326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115502013.006, "dur": 5.982, + "args": { + "External id": 229528,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115502014.389, "dur": 3.888, + "args": { + "External id": 229529,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115502016.426, "dur": 1.634, + "args": { + "External id": 229530,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115502021.409, "dur": 48.786, + "args": { + "External id": 229531,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115502022.821, "dur": 46.786, + "args": { + "External id": 229532,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115502073.764, "dur": 15.576, + "args": { + "External id": 229533,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 8332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115502095.092, "dur": 4.040, + "args": { + "External id": 229534,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115502097.449, "dur": 0.822, + "args": { + "External id": 229535,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "25165824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115502102.903, "dur": 47.429, + "args": { + "External id": 229536,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 8335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115502104.085, "dur": 4.704, + "args": { + "External id": 229537,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 8336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115502105.041, "dur": 3.212, + "args": { + "External id": 229538,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 8337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115502106.976, "dur": 1.119, + "args": { + "External id": 229539,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 8338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115502109.494, "dur": 40.414, + "args": { + "External id": 229540,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115502110.249, "dur": 39.030, + "args": { + "External id": 229541,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115502154.107, "dur": 3.404, + "args": { + "External id": 229542,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115502155.756, "dur": 0.620, + "args": { + "External id": 229543,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115502162.603, "dur": 1.330, + "args": { + "External id": 229544,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115502171.215, "dur": 8.297, + "args": { + "External id": 229545,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115502173.350, "dur": 5.882, + "args": { + "External id": 229546,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115502266.415, "dur": 174.757, + "args": { + "External id": 229547,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115502268.437, "dur": 2.385, + "args": { + "External id": 229548,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115502272.280, "dur": 168.465, + "args": { + "External id": 229549,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115502274.200, "dur": 0.354, + "args": { + "External id": 229550,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115502275.706, "dur": 22.050, + "args": { + "External id": 229551,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115502299.442, "dur": 3.376, + "args": { + "External id": 229552,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115502301.420, "dur": 1.137, + "args": { + "External id": 229553,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115502303.783, "dur": 23.423, + "args": { + "External id": 229554,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115502304.931, "dur": 1.771, + "args": { + "External id": 229555,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115502307.748, "dur": 19.070, + "args": { + "External id": 229556,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115502312.665, "dur": 2.670, + "args": { + "External id": 229557,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115502328.723, "dur": 18.523, + "args": { + "External id": 229558,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115502348.660, "dur": 11.054, + "args": { + "External id": 229559,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115502362.157, "dur": 15.085, + "args": { + "External id": 229560,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115502378.590, "dur": 12.939, + "args": { + "External id": 229561,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115502393.196, "dur": 19.950, + "args": { + "External id": 229562,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115502395.021, "dur": 1.657, + "args": { + "External id": 229563,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115502398.667, "dur": 0.908, + "args": { + "External id": 229564,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115502414.504, "dur": 12.549, + "args": { + "External id": 229565,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115502428.268, "dur": 11.515, + "args": { + "External id": 229566,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115502446.821, "dur": 1.418, + "args": { + "External id": 229567,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115502456.445, "dur": 3.503, + "args": { + "External id": 229568,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115502458.450, "dur": 0.531, + "args": { + "External id": 229569,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115502541.226, "dur": 45.528, + "args": { + "External id": 229570,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 8369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115502591.578, "dur": 6.044, + "args": { + "External id": 229571,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115502594.840, "dur": 1.461, + "args": { + "External id": 229572,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "25165824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115502599.146, "dur": 23.226, + "args": { + "External id": 229573,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 8372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115502626.742, "dur": 5.233, + "args": { + "External id": 229574,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115502628.123, "dur": 3.232, + "args": { + "External id": 229575,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115502630.133, "dur": 0.990, + "args": { + "External id": 229576,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115502634.162, "dur": 75.191, + "args": { + "External id": 229577,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115502635.098, "dur": 73.088, + "args": { + "External id": 229578,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115502714.877, "dur": 15.024, + "args": { + "External id": 229579,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 8378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115502736.296, "dur": 4.997, + "args": { + "External id": 229580,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115502739.366, "dur": 0.846, + "args": { + "External id": 229581,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115502745.286, "dur": 52.399, + "args": { + "External id": 229582,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 8381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115502746.508, "dur": 5.997, + "args": { + "External id": 229583,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 8382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115502747.489, "dur": 4.445, + "args": { + "External id": 229584,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 8383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115502749.233, "dur": 2.551, + "args": { + "External id": 229585,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 8384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115502753.305, "dur": 43.892, + "args": { + "External id": 229586,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115502754.061, "dur": 42.197, + "args": { + "External id": 229587,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115502801.714, "dur": 3.927, + "args": { + "External id": 229588,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115502803.680, "dur": 0.817, + "args": { + "External id": 229589,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115502811.542, "dur": 1.628, + "args": { + "External id": 229590,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115502820.684, "dur": 6.579, + "args": { + "External id": 229591,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115502822.926, "dur": 4.065, + "args": { + "External id": 229592,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115502915.030, "dur": 174.243, + "args": { + "External id": 229593,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115502917.710, "dur": 2.213, + "args": { + "External id": 229594,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115502921.827, "dur": 166.913, + "args": { + "External id": 229595,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115502923.547, "dur": 0.574, + "args": { + "External id": 229596,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115502928.371, "dur": 19.727, + "args": { + "External id": 229597,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115502949.731, "dur": 4.018, + "args": { + "External id": 229598,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115502952.036, "dur": 1.277, + "args": { + "External id": 229599,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115502954.596, "dur": 23.560, + "args": { + "External id": 229600,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115502955.672, "dur": 3.711, + "args": { + "External id": 229601,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115502960.569, "dur": 17.325, + "args": { + "External id": 229602,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115502963.512, "dur": 3.064, + "args": { + "External id": 229603,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115502979.531, "dur": 18.749, + "args": { + "External id": 229604,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115502999.846, "dur": 12.639, + "args": { + "External id": 229605,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115503015.255, "dur": 12.554, + "args": { + "External id": 229606,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115503029.081, "dur": 11.767, + "args": { + "External id": 229607,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115503042.599, "dur": 18.819, + "args": { + "External id": 229608,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115503044.575, "dur": 1.664, + "args": { + "External id": 229609,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115503048.145, "dur": 0.983, + "args": { + "External id": 229610,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115503062.751, "dur": 11.115, + "args": { + "External id": 229611,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115503075.202, "dur": 12.604, + "args": { + "External id": 229612,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115503095.146, "dur": 1.669, + "args": { + "External id": 229613,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115503105.531, "dur": 3.597, + "args": { + "External id": 229614,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115503107.752, "dur": 0.330, + "args": { + "External id": 229615,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115503170.177, "dur": 40.166, + "args": { + "External id": 229616,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 8415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115503214.884, "dur": 4.810, + "args": { + "External id": 229617,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115503217.738, "dur": 0.953, + "args": { + "External id": 229618,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115503221.275, "dur": 21.149, + "args": { + "External id": 229619,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 8418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115503246.884, "dur": 7.351, + "args": { + "External id": 229620,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115503247.939, "dur": 5.583, + "args": { + "External id": 229621,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115503250.222, "dur": 2.992, + "args": { + "External id": 229622,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115503256.460, "dur": 39.677, + "args": { + "External id": 229623,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115503257.211, "dur": 38.070, + "args": { + "External id": 229624,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115503299.274, "dur": 12.717, + "args": { + "External id": 229625,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 8424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115503317.760, "dur": 4.448, + "args": { + "External id": 229626,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115503320.446, "dur": 0.998, + "args": { + "External id": 229627,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "41943040"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115503325.893, "dur": 47.294, + "args": { + "External id": 229628,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 8427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115503326.859, "dur": 4.239, + "args": { + "External id": 229629,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 8428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115503327.952, "dur": 2.653, + "args": { + "External id": 229630,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 8429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115503329.735, "dur": 0.723, + "args": { + "External id": 229631,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 8430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115503331.762, "dur": 41.048, + "args": { + "External id": 229632,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115503332.597, "dur": 39.604, + "args": { + "External id": 229633,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115503376.648, "dur": 4.017, + "args": { + "External id": 229634,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115503378.830, "dur": 0.757, + "args": { + "External id": 229635,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115503385.356, "dur": 1.417, + "args": { + "External id": 229636,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115503394.246, "dur": 6.629, + "args": { + "External id": 229637,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115503396.405, "dur": 4.184, + "args": { + "External id": 229638,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115503477.169, "dur": 240.560, + "args": { + "External id": 229639,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115503478.943, "dur": 2.342, + "args": { + "External id": 229640,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115503485.049, "dur": 232.064, + "args": { + "External id": 229641,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115503486.491, "dur": 0.326, + "args": { + "External id": 229642,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115503487.902, "dur": 39.059, + "args": { + "External id": 229643,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115503529.300, "dur": 5.619, + "args": { + "External id": 229644,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115503531.697, "dur": 2.908, + "args": { + "External id": 229645,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115503535.948, "dur": 23.509, + "args": { + "External id": 229646,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115503537.218, "dur": 1.713, + "args": { + "External id": 229647,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115503540.489, "dur": 18.739, + "args": { + "External id": 229648,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115503543.179, "dur": 2.940, + "args": { + "External id": 229649,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115503560.828, "dur": 20.380, + "args": { + "External id": 229650,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115503582.422, "dur": 12.953, + "args": { + "External id": 229651,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115503598.199, "dur": 15.496, + "args": { + "External id": 229652,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115503614.978, "dur": 13.511, + "args": { + "External id": 229653,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115503630.154, "dur": 53.891, + "args": { + "External id": 229654,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115503632.635, "dur": 2.049, + "args": { + "External id": 229655,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115503636.775, "dur": 0.936, + "args": { + "External id": 229656,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115503687.290, "dur": 14.660, + "args": { + "External id": 229657,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115503703.255, "dur": 12.373, + "args": { + "External id": 229658,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115503725.336, "dur": 2.800, + "args": { + "External id": 229659,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115503752.582, "dur": 4.276, + "args": { + "External id": 229660,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115503755.097, "dur": 0.772, + "args": { + "External id": 229661,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115503829.301, "dur": 51.882, + "args": { + "External id": 229662,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 8461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115503886.270, "dur": 7.196, + "args": { + "External id": 229663,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115503889.147, "dur": 3.292, + "args": { + "External id": 229664,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "41943040"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115503895.112, "dur": 24.786, + "args": { + "External id": 229665,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 8464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115503924.488, "dur": 6.225, + "args": { + "External id": 229666,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115503926.377, "dur": 3.547, + "args": { + "External id": 229667,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115503928.432, "dur": 1.300, + "args": { + "External id": 229668,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115503933.091, "dur": 41.312, + "args": { + "External id": 229669,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115503934.576, "dur": 39.143, + "args": { + "External id": 229670,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115503977.909, "dur": 17.725, + "args": { + "External id": 229671,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 8470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115504001.129, "dur": 3.977, + "args": { + "External id": 229672,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115504003.506, "dur": 0.677, + "args": { + "External id": 229673,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115504009.141, "dur": 78.906, + "args": { + "External id": 229674,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 8473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115504010.071, "dur": 3.713, + "args": { + "External id": 229675,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 8474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115504010.907, "dur": 2.387, + "args": { + "External id": 229676,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 8475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115504012.387, "dur": 0.779, + "args": { + "External id": 229677,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 8476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115504014.382, "dur": 73.276, + "args": { + "External id": 229678,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115504015.321, "dur": 71.756, + "args": { + "External id": 229679,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115504091.897, "dur": 3.555, + "args": { + "External id": 229680,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115504093.452, "dur": 0.889, + "args": { + "External id": 229681,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115504101.221, "dur": 1.563, + "args": { + "External id": 229682,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115504110.712, "dur": 7.359, + "args": { + "External id": 229683,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115504113.452, "dur": 4.325, + "args": { + "External id": 229684,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115504198.397, "dur": 169.054, + "args": { + "External id": 229685,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115504200.528, "dur": 4.007, + "args": { + "External id": 229686,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115504205.935, "dur": 161.012, + "args": { + "External id": 229687,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115504207.201, "dur": 0.510, + "args": { + "External id": 229688,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115504208.933, "dur": 19.351, + "args": { + "External id": 229689,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115504229.644, "dur": 5.525, + "args": { + "External id": 229690,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115504234.190, "dur": 0.675, + "args": { + "External id": 229691,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115504236.181, "dur": 19.980, + "args": { + "External id": 229692,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115504237.362, "dur": 1.602, + "args": { + "External id": 229693,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115504240.130, "dur": 15.787, + "args": { + "External id": 229694,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115504242.637, "dur": 2.582, + "args": { + "External id": 229695,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115504257.532, "dur": 19.581, + "args": { + "External id": 229696,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115504278.504, "dur": 12.504, + "args": { + "External id": 229697,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115504293.544, "dur": 12.603, + "args": { + "External id": 229698,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115504307.554, "dur": 11.039, + "args": { + "External id": 229699,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115504320.243, "dur": 20.862, + "args": { + "External id": 229700,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115504324.606, "dur": 1.430, + "args": { + "External id": 229701,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115504328.413, "dur": 1.236, + "args": { + "External id": 229702,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115504342.799, "dur": 11.015, + "args": { + "External id": 229703,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115504354.788, "dur": 10.913, + "args": { + "External id": 229704,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115504372.507, "dur": 1.503, + "args": { + "External id": 229705,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115504382.100, "dur": 3.790, + "args": { + "External id": 229706,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115504384.110, "dur": 0.528, + "args": { + "External id": 229707,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115504443.062, "dur": 36.791, + "args": { + "External id": 229708,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 8507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115504483.797, "dur": 5.081, + "args": { + "External id": 229709,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115504486.909, "dur": 0.909, + "args": { + "External id": 229710,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115504490.041, "dur": 39.849, + "args": { + "External id": 229711,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 8510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115504535.863, "dur": 6.210, + "args": { + "External id": 229712,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115504537.558, "dur": 3.760, + "args": { + "External id": 229713,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115504539.646, "dur": 1.429, + "args": { + "External id": 229714,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115504545.029, "dur": 42.537, + "args": { + "External id": 229715,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115504546.356, "dur": 40.604, + "args": { + "External id": 229716,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115504591.419, "dur": 14.104, + "args": { + "External id": 229717,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 8516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115504611.086, "dur": 4.209, + "args": { + "External id": 229718,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115504613.597, "dur": 0.798, + "args": { + "External id": 229719,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "58720256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 4183440, "tid": 4183440, + "ts": 667115504619.308, "dur": 80.534, + "args": { + "External id": 229720,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [32000, 1024], []], "Ev Idx": 8519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115504620.432, "dur": 4.364, + "args": { + "External id": 229721,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 8520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115504621.499, "dur": 2.791, + "args": { + "External id": 229722,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32000, 1024], [], []], "Ev Idx": 8521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115504623.333, "dur": 0.822, + "args": { + "External id": 229723,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32000]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32000, 1024], [], [], []], "Ev Idx": 8522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115504625.379, "dur": 73.777, + "args": { + "External id": 229724,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115504626.431, "dur": 71.676, + "args": { + "External id": 229725,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [1, 1024]], "Input Dims": [[8192, 1024], [1024, 32000]], "Ev Idx": 8524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115504705.768, "dur": 5.437, + "args": { + "External id": 229726,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115504708.742, "dur": 1.045, + "args": { + "External id": 229727,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115504717.880, "dur": 1.698, + "args": { + "External id": 229728,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 4183440, "tid": 4183440, + "ts": 667115504727.060, "dur": 7.937, + "args": { + "External id": 229729,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115504729.721, "dur": 5.049, + "args": { + "External id": 229730,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115504818.569, "dur": 180.542, + "args": { + "External id": 229731,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115504823.284, "dur": 2.573, + "args": { + "External id": 229732,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 4183440, "tid": 4183440, + "ts": 667115504827.524, "dur": 171.032, + "args": { + "External id": 229733,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 4183440, "tid": 4183440, + "ts": 667115504829.212, "dur": 0.478, + "args": { + "External id": 229734,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 4183440, "tid": 4183440, + "ts": 667115504831.047, "dur": 20.478, + "args": { + "External id": 229735,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 4183440, "tid": 4183440, + "ts": 667115504852.991, "dur": 5.891, + "args": { + "External id": 229736,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115504857.363, "dur": 1.238, + "args": { + "External id": 229737,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115504859.824, "dur": 20.730, + "args": { + "External id": 229738,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115504860.953, "dur": 1.495, + "args": { + "External id": 229739,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115504863.761, "dur": 16.569, + "args": { + "External id": 229740,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115504866.579, "dur": 2.572, + "args": { + "External id": 229741,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115504881.760, "dur": 21.297, + "args": { + "External id": 229742,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115504904.432, "dur": 12.300, + "args": { + "External id": 229743,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 4183440, "tid": 4183440, + "ts": 667115504919.670, "dur": 13.022, + "args": { + "External id": 229744,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 4183440, "tid": 4183440, + "ts": 667115504934.126, "dur": 11.379, + "args": { + "External id": 229745,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115504947.124, "dur": 19.324, + "args": { + "External id": 229746,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115504949.025, "dur": 1.821, + "args": { + "External id": 229747,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115504952.884, "dur": 1.153, + "args": { + "External id": 229748,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 4183440, "tid": 4183440, + "ts": 667115504967.834, "dur": 13.842, + "args": { + "External id": 229749,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115504982.741, "dur": 14.543, + "args": { + "External id": 229750,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115505004.938, "dur": 1.879, + "args": { + "External id": 229751,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115505015.194, "dur": 3.021, + "args": { + "External id": 229752,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115505016.901, "dur": 0.276, + "args": { + "External id": 229753,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115505079.941, "dur": 44.994, + "args": { + "External id": 229754,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [1024, 1]], "Input Dims": [[8192, 32000], [32000, 1024]], "Ev Idx": 8553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 4183440, "tid": 4183440, + "ts": 667115505129.217, "dur": 14.452, + "args": { + "External id": 229755,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], [], [], []], "Input Dims": [[65536, 1024], [], [], [], []], "Ev Idx": 8554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115505141.235, "dur": 1.083, + "args": { + "External id": 229756,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1024]", "[1024, 1]", "58720256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[65536, 1024], [], [], []], "Ev Idx": 8555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115505145.148, "dur": 23.033, + "args": { + "External id": 229757,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[8192, 1024], [8192, 1024], []], "Ev Idx": 8556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 4183440, "tid": 4183440, + "ts": 667115505172.590, "dur": 7.548, + "args": { + "External id": 229758,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 4183440, "tid": 4183440, + "ts": 667115505173.858, "dur": 5.615, + "args": { + "External id": 229759,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115505176.162, "dur": 3.026, + "args": { + "External id": 229760,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 4183440, "tid": 4183440, + "ts": 667115505182.907, "dur": 41.763, + "args": { + "External id": 229761,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 4183440, "tid": 4183440, + "ts": 667115505183.710, "dur": 40.174, + "args": { + "External id": 229762,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [1024, 1]], "Input Dims": [[32000, 8192], [8192, 1024]], "Ev Idx": 8561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115505227.761, "dur": 13.052, + "args": { + "External id": 229763,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 8562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115505245.550, "dur": 22.248, + "args": { + "External id": 229764,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 8563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 4183440, "tid": 4183440, + "ts": 667115505248.035, "dur": 19.244, + "args": { + "External id": 229765,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115505253.364, "dur": 1.066, + "args": { + "External id": 229766,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115505272.709, "dur": 24.847, + "args": { + "External id": 229767,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], []], "Input Dims": [[32000, 1024], [], [], [], [], []], "Ev Idx": 8566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 4183440, "tid": 4183440, + "ts": 667115505274.586, "dur": 22.767, + "args": { + "External id": 229768,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1024, 1], [], [], [], [], [], []], "Input Dims": [[32000, 1024], [], [], [], [], [], []], "Ev Idx": 8567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115505279.479, "dur": 3.608, + "args": { + "External id": 229769,"Record function id": 0, "Concrete Inputs": ["[32000, 1024]", "[1024, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115505284.660, "dur": 12.239, + "args": { + "External id": 229770,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[1024, 1], [1024, 1], []], "Input Dims": [[32000, 1024], [32000, 1024], []], "Ev Idx": 8569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 4183440, + "ts": 667115505309.357, "dur": 5.101, + "args": { + "External id": 229771,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 8570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 4183440, + "ts": 667115505311.504, "dur": 2.723, + "args": { + "External id": 229772,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[65536, 1024]], "Ev Idx": 8571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 4183440, "tid": 4183440, + "ts": 667115505315.678, "dur": 1.671, + "args": { + "External id": 229773,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 8572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 4183440, "tid": 4183440, + "ts": 667115505316.639, "dur": 0.609, + "args": { + "External id": 229774,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32000, 1024]], "Ev Idx": 8573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115505359.305, "dur": 20.170, + "args": { + "External id": 229775,"Sequence number": 2757956, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 8574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 4183440, "tid": 4183440, + "ts": 667115505381.660, "dur": 13.480, + "args": { + "External id": 229776,"Sequence number": 2757957, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 8575 + } + }, + { + "ph": "s", "id": 2, "pid": 4183440, "tid": 4183440, "ts": 667115505381.660, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward", "pid": 4183440, "tid": 4183440, + "ts": 667115505523.009, "dur": 42.225, + "args": { + "External id": 229777,"Record function id": 0, "Ev Idx": 8576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 4183440, "tid": 4183440, + "ts": 667115505713.910, "dur": 40.130, + "args": { + "External id": 229778,"Sequence number": 2757958, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 8577 + } + }, + { + "ph": "s", "id": 1, "pid": 4183440, "tid": 4183440, "ts": 667115505713.910, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ones_like", "pid": 4183440, "tid": 4183440, + "ts": 667115505812.118, "dur": 29.916, + "args": { + "External id": 229779,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "1"], "Input type": ["float", "", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 8578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115505813.829, "dur": 8.721, + "args": { + "External id": 229780,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "1"], "Input type": ["float", "", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 8579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115505817.798, "dur": 4.172, + "args": { + "External id": 229781,"Record function id": 0, "Concrete Inputs": ["[1]", "[1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115505824.014, "dur": 17.724, + "args": { + "External id": 229782,"Record function id": 0, "Concrete Inputs": ["", "1."], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 8581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 4183440, "tid": 4183440, + "ts": 667115955586.105, "dur": 44.948, + "args": { + "External id": 229783,"Sequence number": 2757959, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 4183440, "tid": 4183440, + "ts": 667115955637.777, "dur": 45.791, + "args": { + "External id": 229784,"Sequence number": 2757960, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 8583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 4183440, "tid": 4183440, + "ts": 667115955756.869, "dur": 25.714, + "args": { + "External id": 229785,"Sequence number": 2757961, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "long int", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 8584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 4183440, "tid": 4183440, + "ts": 667115956170.006, "dur": 20.518, + "args": { + "External id": 229786,"Sequence number": 2757962, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "long int", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 8585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 4183440, "tid": 4183440, + "ts": 667115956196.061, "dur": 12.569, + "args": { + "External id": 229787,"Sequence number": 2757963, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "long int", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 8586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_norm", "pid": 4183440, "tid": 4183440, + "ts": 667115957490.364, "dur": 2322.361, + "args": { + "External id": 229788,"Record function id": 0, "Concrete Inputs": ["", "2.", ""], "Input type": ["TensorList", "Scalar", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 8587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_norm", "pid": 4183440, "tid": 4183440, + "ts": 667115957985.402, "dur": 642.710, + "args": { + "External id": 229789,"Record function id": 0, "Concrete Inputs": ["", "2.", ""], "Input type": ["TensorList", "Scalar", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 8588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 4183440, "tid": 4183440, + "ts": 667115958003.987, "dur": 70.483, + "args": { + "External id": 229790,"Record function id": 0, "Concrete Inputs": ["[13797]", "6", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 8589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115958010.679, "dur": 12.510, + "args": { + "External id": 229791,"Record function id": 0, "Concrete Inputs": ["[13797]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 4183440, "tid": 4183440, + "ts": 667115958026.174, "dur": 47.961, + "args": { + "External id": 229792,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[13797]], "Ev Idx": 8591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 4183440, "tid": 4183440, + "ts": 667115958028.149, "dur": 45.418, + "args": { + "External id": 229793,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[13797], []], "Ev Idx": 8592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959839.275, "dur": 3.970, + "args": { + "External id": 229794,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959845.316, "dur": 0.454, + "args": { + "External id": 229795,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959846.974, "dur": 0.331, + "args": { + "External id": 229796,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959848.445, "dur": 0.496, + "args": { + "External id": 229797,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959850.074, "dur": 0.360, + "args": { + "External id": 229798,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959851.741, "dur": 0.226, + "args": { + "External id": 229799,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959853.155, "dur": 0.253, + "args": { + "External id": 229800,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959855.656, "dur": 0.421, + "args": { + "External id": 229801,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959856.934, "dur": 0.397, + "args": { + "External id": 229802,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959858.394, "dur": 0.288, + "args": { + "External id": 229803,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959859.512, "dur": 0.389, + "args": { + "External id": 229804,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959860.710, "dur": 0.412, + "args": { + "External id": 229805,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959862.056, "dur": 0.312, + "args": { + "External id": 229806,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959863.298, "dur": 0.221, + "args": { + "External id": 229807,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959864.573, "dur": 0.199, + "args": { + "External id": 229808,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959866.994, "dur": 0.409, + "args": { + "External id": 229809,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959868.463, "dur": 0.211, + "args": { + "External id": 229810,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959869.813, "dur": 0.207, + "args": { + "External id": 229811,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959870.859, "dur": 0.216, + "args": { + "External id": 229812,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959872.157, "dur": 0.212, + "args": { + "External id": 229813,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959873.339, "dur": 0.239, + "args": { + "External id": 229814,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959874.383, "dur": 0.200, + "args": { + "External id": 229815,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959875.379, "dur": 0.346, + "args": { + "External id": 229816,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959878.252, "dur": 3.601, + "args": { + "External id": 229817,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959882.659, "dur": 0.206, + "args": { + "External id": 229818,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959883.808, "dur": 0.209, + "args": { + "External id": 229819,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959884.808, "dur": 0.207, + "args": { + "External id": 229820,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959885.906, "dur": 0.227, + "args": { + "External id": 229821,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959886.980, "dur": 0.210, + "args": { + "External id": 229822,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959888.066, "dur": 0.199, + "args": { + "External id": 229823,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959889.185, "dur": 0.206, + "args": { + "External id": 229824,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959891.385, "dur": 0.201, + "args": { + "External id": 229825,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959892.669, "dur": 0.200, + "args": { + "External id": 229826,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959894.265, "dur": 0.520, + "args": { + "External id": 229827,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959895.583, "dur": 0.449, + "args": { + "External id": 229828,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959896.904, "dur": 0.430, + "args": { + "External id": 229829,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959898.297, "dur": 0.331, + "args": { + "External id": 229830,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959899.416, "dur": 0.197, + "args": { + "External id": 229831,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959900.574, "dur": 0.339, + "args": { + "External id": 229832,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959902.850, "dur": 0.369, + "args": { + "External id": 229833,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959904.038, "dur": 0.462, + "args": { + "External id": 229834,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959905.428, "dur": 0.386, + "args": { + "External id": 229835,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959906.608, "dur": 0.411, + "args": { + "External id": 229836,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959907.806, "dur": 0.424, + "args": { + "External id": 229837,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959909.022, "dur": 0.411, + "args": { + "External id": 229838,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959910.268, "dur": 0.232, + "args": { + "External id": 229839,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959911.292, "dur": 0.204, + "args": { + "External id": 229840,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959914.536, "dur": 0.216, + "args": { + "External id": 229841,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959915.615, "dur": 0.208, + "args": { + "External id": 229842,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959916.840, "dur": 0.199, + "args": { + "External id": 229843,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959917.877, "dur": 0.205, + "args": { + "External id": 229844,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959919.060, "dur": 0.222, + "args": { + "External id": 229845,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959920.069, "dur": 0.204, + "args": { + "External id": 229846,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959921.355, "dur": 0.228, + "args": { + "External id": 229847,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959922.375, "dur": 0.202, + "args": { + "External id": 229848,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959925.116, "dur": 0.197, + "args": { + "External id": 229849,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959926.116, "dur": 0.202, + "args": { + "External id": 229850,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959927.271, "dur": 0.198, + "args": { + "External id": 229851,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959928.298, "dur": 0.200, + "args": { + "External id": 229852,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959929.295, "dur": 0.196, + "args": { + "External id": 229853,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959930.304, "dur": 0.203, + "args": { + "External id": 229854,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959931.458, "dur": 0.195, + "args": { + "External id": 229855,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959932.454, "dur": 0.199, + "args": { + "External id": 229856,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959934.678, "dur": 0.206, + "args": { + "External id": 229857,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959935.697, "dur": 0.200, + "args": { + "External id": 229858,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959936.927, "dur": 3.540, + "args": { + "External id": 229859,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959941.364, "dur": 0.216, + "args": { + "External id": 229860,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959942.449, "dur": 0.211, + "args": { + "External id": 229861,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959943.603, "dur": 0.207, + "args": { + "External id": 229862,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959944.606, "dur": 0.214, + "args": { + "External id": 229863,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959945.709, "dur": 0.208, + "args": { + "External id": 229864,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959947.877, "dur": 0.216, + "args": { + "External id": 229865,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959948.977, "dur": 0.413, + "args": { + "External id": 229866,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959950.188, "dur": 0.414, + "args": { + "External id": 229867,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959951.422, "dur": 0.429, + "args": { + "External id": 229868,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959952.653, "dur": 0.414, + "args": { + "External id": 229869,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959953.954, "dur": 0.315, + "args": { + "External id": 229870,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959955.931, "dur": 0.230, + "args": { + "External id": 229871,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959957.084, "dur": 0.456, + "args": { + "External id": 229872,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959959.113, "dur": 0.383, + "args": { + "External id": 229873,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959960.378, "dur": 0.381, + "args": { + "External id": 229874,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959961.543, "dur": 0.436, + "args": { + "External id": 229875,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959962.771, "dur": 0.472, + "args": { + "External id": 229876,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959964.116, "dur": 0.233, + "args": { + "External id": 229877,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959965.371, "dur": 0.264, + "args": { + "External id": 229878,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959966.549, "dur": 0.195, + "args": { + "External id": 229879,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959967.555, "dur": 0.222, + "args": { + "External id": 229880,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959969.684, "dur": 0.223, + "args": { + "External id": 229881,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959970.807, "dur": 0.227, + "args": { + "External id": 229882,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959971.903, "dur": 0.204, + "args": { + "External id": 229883,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959972.887, "dur": 0.245, + "args": { + "External id": 229884,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959973.989, "dur": 0.194, + "args": { + "External id": 229885,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959974.969, "dur": 0.227, + "args": { + "External id": 229886,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959976.817, "dur": 0.230, + "args": { + "External id": 229887,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115959977.858, "dur": 0.223, + "args": { + "External id": 229888,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960009.466, "dur": 0.332, + "args": { + "External id": 234497,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960010.998, "dur": 0.243, + "args": { + "External id": 234498,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960012.395, "dur": 0.214, + "args": { + "External id": 234499,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960013.421, "dur": 0.201, + "args": { + "External id": 234500,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960014.578, "dur": 0.216, + "args": { + "External id": 234501,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960015.595, "dur": 0.203, + "args": { + "External id": 234502,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960016.596, "dur": 0.204, + "args": { + "External id": 234503,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960017.596, "dur": 0.204, + "args": { + "External id": 234504,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960020.260, "dur": 0.204, + "args": { + "External id": 234505,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960021.267, "dur": 0.200, + "args": { + "External id": 234506,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960022.289, "dur": 0.206, + "args": { + "External id": 234507,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960023.364, "dur": 0.198, + "args": { + "External id": 234508,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960024.367, "dur": 0.206, + "args": { + "External id": 234509,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960025.430, "dur": 0.197, + "args": { + "External id": 234510,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960026.853, "dur": 0.208, + "args": { + "External id": 234511,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960027.857, "dur": 0.196, + "args": { + "External id": 234512,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960030.364, "dur": 0.207, + "args": { + "External id": 234513,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960031.364, "dur": 0.202, + "args": { + "External id": 234514,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960032.375, "dur": 0.205, + "args": { + "External id": 234515,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960033.603, "dur": 0.197, + "args": { + "External id": 234516,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960034.586, "dur": 0.203, + "args": { + "External id": 234517,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960035.581, "dur": 0.201, + "args": { + "External id": 234518,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960036.617, "dur": 0.204, + "args": { + "External id": 234519,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960040.588, "dur": 0.251, + "args": { + "External id": 234520,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960043.097, "dur": 0.205, + "args": { + "External id": 234521,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960044.061, "dur": 0.209, + "args": { + "External id": 234522,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960045.062, "dur": 0.226, + "args": { + "External id": 234523,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960046.125, "dur": 0.210, + "args": { + "External id": 234524,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960047.165, "dur": 0.201, + "args": { + "External id": 234525,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960048.155, "dur": 0.229, + "args": { + "External id": 234526,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960049.166, "dur": 0.200, + "args": { + "External id": 234527,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960050.149, "dur": 0.230, + "args": { + "External id": 234528,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960052.802, "dur": 0.199, + "args": { + "External id": 234529,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960053.872, "dur": 3.517, + "args": { + "External id": 234530,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960059.352, "dur": 0.225, + "args": { + "External id": 234531,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960060.526, "dur": 0.239, + "args": { + "External id": 234532,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960061.556, "dur": 0.223, + "args": { + "External id": 234533,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960062.578, "dur": 0.197, + "args": { + "External id": 234534,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960063.556, "dur": 0.223, + "args": { + "External id": 234535,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960064.572, "dur": 0.236, + "args": { + "External id": 234536,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960067.030, "dur": 0.226, + "args": { + "External id": 234537,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960068.086, "dur": 0.205, + "args": { + "External id": 234538,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960069.088, "dur": 0.224, + "args": { + "External id": 234539,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960070.248, "dur": 0.203, + "args": { + "External id": 234540,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960071.248, "dur": 0.228, + "args": { + "External id": 234541,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960072.372, "dur": 0.244, + "args": { + "External id": 234542,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960073.491, "dur": 0.198, + "args": { + "External id": 234543,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960074.478, "dur": 0.231, + "args": { + "External id": 234544,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960076.836, "dur": 0.206, + "args": { + "External id": 234545,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960077.847, "dur": 0.232, + "args": { + "External id": 234546,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960078.868, "dur": 0.216, + "args": { + "External id": 234547,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960079.878, "dur": 0.228, + "args": { + "External id": 234548,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960080.889, "dur": 0.198, + "args": { + "External id": 234549,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960081.903, "dur": 0.232, + "args": { + "External id": 234550,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960083.272, "dur": 0.198, + "args": { + "External id": 234551,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960084.351, "dur": 0.233, + "args": { + "External id": 234552,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960086.897, "dur": 0.218, + "args": { + "External id": 234553,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960087.900, "dur": 0.235, + "args": { + "External id": 234554,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960088.918, "dur": 0.199, + "args": { + "External id": 234555,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960089.898, "dur": 0.228, + "args": { + "External id": 234556,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960091.006, "dur": 0.199, + "args": { + "External id": 234557,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960092.014, "dur": 0.205, + "args": { + "External id": 234558,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960093.044, "dur": 0.226, + "args": { + "External id": 234559,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960094.127, "dur": 0.237, + "args": { + "External id": 234560,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960095.948, "dur": 0.222, + "args": { + "External id": 234561,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960096.999, "dur": 0.203, + "args": { + "External id": 234562,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960100.061, "dur": 0.211, + "args": { + "External id": 234563,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960101.103, "dur": 0.224, + "args": { + "External id": 234564,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960102.161, "dur": 0.200, + "args": { + "External id": 234565,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960103.156, "dur": 0.207, + "args": { + "External id": 234566,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960104.319, "dur": 0.196, + "args": { + "External id": 234567,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960105.310, "dur": 0.206, + "args": { + "External id": 234568,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960107.541, "dur": 0.218, + "args": { + "External id": 234569,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960108.662, "dur": 0.204, + "args": { + "External id": 234570,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960109.660, "dur": 0.224, + "args": { + "External id": 234571,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960110.746, "dur": 0.217, + "args": { + "External id": 234572,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960111.776, "dur": 0.199, + "args": { + "External id": 234573,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960112.763, "dur": 0.206, + "args": { + "External id": 234574,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960113.955, "dur": 0.195, + "args": { + "External id": 234575,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960114.939, "dur": 0.206, + "args": { + "External id": 234576,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960116.836, "dur": 0.197, + "args": { + "External id": 234577,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960117.899, "dur": 0.203, + "args": { + "External id": 234578,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960118.940, "dur": 0.202, + "args": { + "External id": 234579,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960119.982, "dur": 0.204, + "args": { + "External id": 234580,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960120.972, "dur": 0.200, + "args": { + "External id": 234581,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960121.952, "dur": 0.203, + "args": { + "External id": 234582,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960122.938, "dur": 0.198, + "args": { + "External id": 234583,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960124.064, "dur": 0.205, + "args": { + "External id": 234584,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960126.483, "dur": 0.202, + "args": { + "External id": 234585,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960127.509, "dur": 0.200, + "args": { + "External id": 234586,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960128.602, "dur": 0.208, + "args": { + "External id": 234587,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960129.609, "dur": 0.200, + "args": { + "External id": 234588,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960130.806, "dur": 0.197, + "args": { + "External id": 234589,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960131.862, "dur": 0.206, + "args": { + "External id": 234590,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960132.903, "dur": 0.197, + "args": { + "External id": 234591,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960137.284, "dur": 0.208, + "args": { + "External id": 234592,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960140.139, "dur": 0.196, + "args": { + "External id": 234593,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960141.138, "dur": 0.208, + "args": { + "External id": 234594,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960142.206, "dur": 0.206, + "args": { + "External id": 234595,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960143.201, "dur": 0.207, + "args": { + "External id": 234596,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960144.223, "dur": 0.203, + "args": { + "External id": 234597,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960145.208, "dur": 0.206, + "args": { + "External id": 234598,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960146.228, "dur": 0.198, + "args": { + "External id": 234599,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960147.223, "dur": 0.207, + "args": { + "External id": 234600,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960149.670, "dur": 0.196, + "args": { + "External id": 234601,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960150.668, "dur": 0.236, + "args": { + "External id": 234602,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960152.108, "dur": 0.198, + "args": { + "External id": 234603,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960153.156, "dur": 0.200, + "args": { + "External id": 234604,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960159.139, "dur": 0.221, + "args": { + "External id": 234605,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960160.454, "dur": 0.220, + "args": { + "External id": 234606,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960161.494, "dur": 0.209, + "args": { + "External id": 234607,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960162.487, "dur": 0.221, + "args": { + "External id": 234608,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960164.803, "dur": 0.211, + "args": { + "External id": 234609,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960166.066, "dur": 0.194, + "args": { + "External id": 234610,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960167.050, "dur": 0.203, + "args": { + "External id": 234611,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960168.038, "dur": 0.218, + "args": { + "External id": 234612,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960169.041, "dur": 0.202, + "args": { + "External id": 234613,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960170.027, "dur": 0.199, + "args": { + "External id": 234614,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960171.085, "dur": 0.202, + "args": { + "External id": 234615,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960172.097, "dur": 0.214, + "args": { + "External id": 234616,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960174.170, "dur": 0.206, + "args": { + "External id": 234617,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960175.169, "dur": 0.201, + "args": { + "External id": 234618,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960176.263, "dur": 0.203, + "args": { + "External id": 234619,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115960177.263, "dur": 0.196, + "args": { + "External id": 234620,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 8811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 4183440, "tid": 4183440, + "ts": 667115960221.285, "dur": 1147.960, + "args": { + "External id": 234621,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 4183440, "tid": 4183440, + "ts": 667115960584.219, "dur": 722.293, + "args": { + "External id": 234622,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960590.556, "dur": 7.493, + "args": { + "External id": 234623,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960594.472, "dur": 2.987, + "args": { + "External id": 234624,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960598.804, "dur": 3.442, + "args": { + "External id": 234625,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960599.500, "dur": 2.579, + "args": { + "External id": 234626,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960602.655, "dur": 2.744, + "args": { + "External id": 234627,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960604.493, "dur": 0.611, + "args": { + "External id": 234628,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960605.674, "dur": 1.262, + "args": { + "External id": 234629,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960606.083, "dur": 0.781, + "args": { + "External id": 234630,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960608.727, "dur": 4.810, + "args": { + "External id": 234631,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960612.701, "dur": 0.769, + "args": { + "External id": 234632,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960613.825, "dur": 1.302, + "args": { + "External id": 234633,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960614.286, "dur": 0.537, + "args": { + "External id": 234634,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960615.362, "dur": 1.034, + "args": { + "External id": 234635,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960615.725, "dur": 0.602, + "args": { + "External id": 234636,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960616.796, "dur": 6.403, + "args": { + "External id": 234637,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960622.319, "dur": 0.807, + "args": { + "External id": 234638,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960623.426, "dur": 1.310, + "args": { + "External id": 234639,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960623.856, "dur": 0.817, + "args": { + "External id": 234640,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960624.965, "dur": 3.100, + "args": { + "External id": 234641,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960625.410, "dur": 2.566, + "args": { + "External id": 234642,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960628.316, "dur": 2.604, + "args": { + "External id": 234643,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960629.998, "dur": 0.858, + "args": { + "External id": 234644,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960631.532, "dur": 1.195, + "args": { + "External id": 234645,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960631.893, "dur": 0.765, + "args": { + "External id": 234646,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960634.199, "dur": 4.218, + "args": { + "External id": 234647,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960637.601, "dur": 0.745, + "args": { + "External id": 234648,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960638.660, "dur": 1.291, + "args": { + "External id": 234649,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960639.258, "dur": 0.627, + "args": { + "External id": 234650,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960640.225, "dur": 1.304, + "args": { + "External id": 234651,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960640.598, "dur": 0.863, + "args": { + "External id": 234652,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960641.756, "dur": 4.234, + "args": { + "External id": 234653,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960645.505, "dur": 0.413, + "args": { + "External id": 234654,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960646.416, "dur": 0.900, + "args": { + "External id": 234655,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960646.780, "dur": 0.472, + "args": { + "External id": 234656,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960647.540, "dur": 2.643, + "args": { + "External id": 234657,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960647.898, "dur": 2.211, + "args": { + "External id": 234658,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960650.411, "dur": 2.680, + "args": { + "External id": 234659,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960652.076, "dur": 0.953, + "args": { + "External id": 234660,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960679.651, "dur": 3.038, + "args": { + "External id": 234661,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960681.260, "dur": 1.147, + "args": { + "External id": 234662,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960684.741, "dur": 4.626, + "args": { + "External id": 234663,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960688.599, "dur": 0.704, + "args": { + "External id": 234664,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960689.644, "dur": 1.289, + "args": { + "External id": 234665,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960690.051, "dur": 0.816, + "args": { + "External id": 234666,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960691.181, "dur": 0.915, + "args": { + "External id": 234667,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960691.560, "dur": 0.460, + "args": { + "External id": 234668,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960692.325, "dur": 3.380, + "args": { + "External id": 234669,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960694.989, "dur": 0.556, + "args": { + "External id": 234670,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960695.936, "dur": 1.113, + "args": { + "External id": 234671,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960696.299, "dur": 0.689, + "args": { + "External id": 234672,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960697.319, "dur": 2.574, + "args": { + "External id": 234673,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960697.696, "dur": 2.115, + "args": { + "External id": 234674,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960700.143, "dur": 2.354, + "args": { + "External id": 234675,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960701.818, "dur": 0.617, + "args": { + "External id": 234676,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960702.726, "dur": 1.256, + "args": { + "External id": 234677,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960703.085, "dur": 0.682, + "args": { + "External id": 234678,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960704.863, "dur": 4.465, + "args": { + "External id": 234679,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960708.666, "dur": 0.596, + "args": { + "External id": 234680,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960709.570, "dur": 1.249, + "args": { + "External id": 234681,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960709.926, "dur": 0.618, + "args": { + "External id": 234682,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960711.315, "dur": 1.489, + "args": { + "External id": 234683,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960711.688, "dur": 1.048, + "args": { + "External id": 234684,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960713.031, "dur": 4.071, + "args": { + "External id": 234685,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960716.203, "dur": 0.836, + "args": { + "External id": 234686,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960717.344, "dur": 1.510, + "args": { + "External id": 234687,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960717.698, "dur": 0.872, + "args": { + "External id": 234688,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960719.076, "dur": 2.830, + "args": { + "External id": 234689,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960719.455, "dur": 2.172, + "args": { + "External id": 234690,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960722.147, "dur": 2.817, + "args": { + "External id": 234691,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960724.251, "dur": 0.630, + "args": { + "External id": 234692,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960725.188, "dur": 1.245, + "args": { + "External id": 234693,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960725.561, "dur": 0.801, + "args": { + "External id": 234694,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960726.741, "dur": 4.280, + "args": { + "External id": 234695,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960730.274, "dur": 0.682, + "args": { + "External id": 234696,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960731.376, "dur": 1.045, + "args": { + "External id": 234697,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960731.773, "dur": 0.586, + "args": { + "External id": 234698,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960732.697, "dur": 1.103, + "args": { + "External id": 234699,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960733.068, "dur": 0.661, + "args": { + "External id": 234700,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960734.089, "dur": 3.771, + "args": { + "External id": 234701,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960736.762, "dur": 0.827, + "args": { + "External id": 234702,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960738.115, "dur": 1.174, + "args": { + "External id": 234703,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960738.467, "dur": 0.757, + "args": { + "External id": 234704,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960739.534, "dur": 2.911, + "args": { + "External id": 234705,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960739.899, "dur": 2.471, + "args": { + "External id": 234706,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960742.768, "dur": 1.727, + "args": { + "External id": 234707,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960743.584, "dur": 0.843, + "args": { + "External id": 234708,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960744.853, "dur": 1.420, + "args": { + "External id": 234709,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960745.247, "dur": 0.761, + "args": { + "External id": 234710,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960746.513, "dur": 2.973, + "args": { + "External id": 234711,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960748.893, "dur": 0.520, + "args": { + "External id": 234712,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960749.759, "dur": 1.324, + "args": { + "External id": 234713,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960750.120, "dur": 0.900, + "args": { + "External id": 234714,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960751.346, "dur": 1.346, + "args": { + "External id": 234715,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960751.705, "dur": 0.828, + "args": { + "External id": 234716,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960752.951, "dur": 3.548, + "args": { + "External id": 234717,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960755.608, "dur": 0.734, + "args": { + "External id": 234718,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960756.749, "dur": 1.482, + "args": { + "External id": 234719,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960757.120, "dur": 0.948, + "args": { + "External id": 234720,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960758.666, "dur": 2.973, + "args": { + "External id": 234721,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960759.062, "dur": 2.417, + "args": { + "External id": 234722,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960761.908, "dur": 1.332, + "args": { + "External id": 234723,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960762.544, "dur": 0.633, + "args": { + "External id": 234724,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960763.482, "dur": 1.269, + "args": { + "External id": 234725,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960763.839, "dur": 0.838, + "args": { + "External id": 234726,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960764.993, "dur": 2.835, + "args": { + "External id": 234727,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960767.344, "dur": 0.414, + "args": { + "External id": 234728,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960768.132, "dur": 1.357, + "args": { + "External id": 234729,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960768.504, "dur": 0.717, + "args": { + "External id": 234730,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960769.758, "dur": 1.201, + "args": { + "External id": 234731,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960770.150, "dur": 0.654, + "args": { + "External id": 234732,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960771.218, "dur": 3.007, + "args": { + "External id": 234733,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960773.384, "dur": 0.681, + "args": { + "External id": 234734,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960774.483, "dur": 1.192, + "args": { + "External id": 234735,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960774.892, "dur": 0.720, + "args": { + "External id": 234736,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960775.926, "dur": 2.826, + "args": { + "External id": 234737,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960776.322, "dur": 2.245, + "args": { + "External id": 234738,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960779.030, "dur": 1.908, + "args": { + "External id": 234739,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960779.830, "dur": 0.952, + "args": { + "External id": 234740,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960781.379, "dur": 1.144, + "args": { + "External id": 234741,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960781.748, "dur": 0.684, + "args": { + "External id": 234742,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960782.787, "dur": 3.523, + "args": { + "External id": 234743,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960785.586, "dur": 0.662, + "args": { + "External id": 234744,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960786.578, "dur": 1.273, + "args": { + "External id": 234745,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960786.952, "dur": 0.520, + "args": { + "External id": 234746,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960788.103, "dur": 1.399, + "args": { + "External id": 234747,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960788.473, "dur": 0.768, + "args": { + "External id": 234748,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960789.753, "dur": 2.968, + "args": { + "External id": 234749,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960791.942, "dur": 0.711, + "args": { + "External id": 234750,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960792.966, "dur": 1.260, + "args": { + "External id": 234751,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960793.317, "dur": 0.849, + "args": { + "External id": 234752,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960794.684, "dur": 2.591, + "args": { + "External id": 234753,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960795.044, "dur": 2.075, + "args": { + "External id": 234754,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960797.691, "dur": 1.724, + "args": { + "External id": 234755,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960798.158, "dur": 1.196, + "args": { + "External id": 234756,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960799.854, "dur": 1.316, + "args": { + "External id": 234757,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960800.244, "dur": 0.855, + "args": { + "External id": 234758,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960801.484, "dur": 3.020, + "args": { + "External id": 234759,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960803.888, "dur": 0.547, + "args": { + "External id": 234760,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960804.962, "dur": 1.024, + "args": { + "External id": 234761,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960805.338, "dur": 0.579, + "args": { + "External id": 234762,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960806.246, "dur": 1.389, + "args": { + "External id": 234763,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960806.655, "dur": 0.909, + "args": { + "External id": 234764,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960807.905, "dur": 2.989, + "args": { + "External id": 234765,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960810.436, "dur": 0.394, + "args": { + "External id": 234766,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960811.181, "dur": 1.059, + "args": { + "External id": 234767,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960811.542, "dur": 0.635, + "args": { + "External id": 234768,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960812.483, "dur": 2.462, + "args": { + "External id": 234769,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960812.861, "dur": 2.008, + "args": { + "External id": 234770,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960815.195, "dur": 1.535, + "args": { + "External id": 234771,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960815.939, "dur": 0.730, + "args": { + "External id": 234772,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960817.208, "dur": 0.904, + "args": { + "External id": 234773,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960817.563, "dur": 0.482, + "args": { + "External id": 234774,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960818.357, "dur": 3.413, + "args": { + "External id": 234775,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960820.794, "dur": 0.901, + "args": { + "External id": 234776,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960822.057, "dur": 1.160, + "args": { + "External id": 234777,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960822.472, "dur": 0.676, + "args": { + "External id": 234778,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960823.598, "dur": 2.190, + "args": { + "External id": 234779,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960823.979, "dur": 1.742, + "args": { + "External id": 234780,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960826.032, "dur": 3.157, + "args": { + "External id": 234781,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960828.327, "dur": 0.801, + "args": { + "External id": 234782,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960829.463, "dur": 1.206, + "args": { + "External id": 234783,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960829.909, "dur": 0.700, + "args": { + "External id": 234784,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960830.929, "dur": 3.175, + "args": { + "External id": 234785,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960831.283, "dur": 2.747, + "args": { + "External id": 234786,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960834.352, "dur": 1.893, + "args": { + "External id": 234787,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960835.012, "dur": 1.171, + "args": { + "External id": 234788,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960836.598, "dur": 1.657, + "args": { + "External id": 234789,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960837.232, "dur": 0.954, + "args": { + "External id": 234790,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960838.565, "dur": 3.117, + "args": { + "External id": 234791,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960841.030, "dur": 0.589, + "args": { + "External id": 234792,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960841.942, "dur": 1.086, + "args": { + "External id": 234793,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960842.321, "dur": 0.642, + "args": { + "External id": 234794,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960843.270, "dur": 1.159, + "args": { + "External id": 234795,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960843.632, "dur": 0.730, + "args": { + "External id": 234796,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960844.865, "dur": 2.837, + "args": { + "External id": 234797,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960847.110, "dur": 0.527, + "args": { + "External id": 234798,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960847.960, "dur": 1.402, + "args": { + "External id": 234799,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960848.330, "dur": 0.965, + "args": { + "External id": 234800,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960849.606, "dur": 2.446, + "args": { + "External id": 234801,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960850.014, "dur": 1.965, + "args": { + "External id": 234802,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960852.318, "dur": 1.545, + "args": { + "External id": 234803,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960853.048, "dur": 0.749, + "args": { + "External id": 234804,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960854.106, "dur": 1.569, + "args": { + "External id": 234805,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960854.475, "dur": 1.133, + "args": { + "External id": 234806,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960855.995, "dur": 3.248, + "args": { + "External id": 234807,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 8998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960858.515, "dur": 0.657, + "args": { + "External id": 234808,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960859.515, "dur": 0.984, + "args": { + "External id": 234809,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960859.911, "dur": 0.527, + "args": { + "External id": 234810,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960860.945, "dur": 1.298, + "args": { + "External id": 234811,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960861.297, "dur": 0.878, + "args": { + "External id": 234812,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960862.585, "dur": 3.083, + "args": { + "External id": 234813,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960865.096, "dur": 0.507, + "args": { + "External id": 234814,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960865.959, "dur": 1.063, + "args": { + "External id": 234815,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960866.367, "dur": 0.592, + "args": { + "External id": 234816,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960867.328, "dur": 3.051, + "args": { + "External id": 234817,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960867.726, "dur": 2.582, + "args": { + "External id": 234818,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960870.631, "dur": 1.325, + "args": { + "External id": 234819,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960871.336, "dur": 0.557, + "args": { + "External id": 234820,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960872.245, "dur": 1.185, + "args": { + "External id": 234821,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960872.625, "dur": 0.739, + "args": { + "External id": 234822,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960873.699, "dur": 3.520, + "args": { + "External id": 234823,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960876.354, "dur": 0.797, + "args": { + "External id": 234824,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960877.495, "dur": 1.436, + "args": { + "External id": 234825,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960877.906, "dur": 0.959, + "args": { + "External id": 234826,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960879.242, "dur": 1.388, + "args": { + "External id": 234827,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960879.597, "dur": 0.962, + "args": { + "External id": 234828,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960880.881, "dur": 2.891, + "args": { + "External id": 234829,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960883.112, "dur": 0.593, + "args": { + "External id": 234830,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960884.047, "dur": 1.037, + "args": { + "External id": 234831,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960884.412, "dur": 0.608, + "args": { + "External id": 234832,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960885.354, "dur": 2.536, + "args": { + "External id": 234833,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960885.750, "dur": 2.062, + "args": { + "External id": 234834,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960888.174, "dur": 1.285, + "args": { + "External id": 234835,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960888.817, "dur": 0.580, + "args": { + "External id": 234836,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960889.917, "dur": 1.301, + "args": { + "External id": 234837,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960890.285, "dur": 0.858, + "args": { + "External id": 234838,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960891.475, "dur": 3.207, + "args": { + "External id": 234839,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960894.019, "dur": 0.598, + "args": { + "External id": 234840,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960894.998, "dur": 1.360, + "args": { + "External id": 234841,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960895.372, "dur": 0.922, + "args": { + "External id": 234842,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960896.732, "dur": 1.389, + "args": { + "External id": 234843,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960897.122, "dur": 0.925, + "args": { + "External id": 234844,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960898.368, "dur": 2.977, + "args": { + "External id": 234845,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960900.536, "dur": 0.740, + "args": { + "External id": 234846,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960901.686, "dur": 1.014, + "args": { + "External id": 234847,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960902.068, "dur": 0.569, + "args": { + "External id": 234848,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960903.040, "dur": 2.468, + "args": { + "External id": 234849,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960903.407, "dur": 1.827, + "args": { + "External id": 234850,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960905.751, "dur": 1.668, + "args": { + "External id": 234851,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960906.387, "dur": 0.963, + "args": { + "External id": 234852,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960907.893, "dur": 1.333, + "args": { + "External id": 234853,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960908.301, "dur": 0.853, + "args": { + "External id": 234854,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960909.570, "dur": 3.515, + "args": { + "External id": 234855,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960912.271, "dur": 0.736, + "args": { + "External id": 234856,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960913.366, "dur": 1.206, + "args": { + "External id": 234857,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960913.779, "dur": 0.720, + "args": { + "External id": 234858,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960914.817, "dur": 1.289, + "args": { + "External id": 234859,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960915.207, "dur": 0.827, + "args": { + "External id": 234860,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960916.543, "dur": 2.876, + "args": { + "External id": 234861,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960918.763, "dur": 0.593, + "args": { + "External id": 234862,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960919.827, "dur": 1.193, + "args": { + "External id": 234863,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960920.297, "dur": 0.660, + "args": { + "External id": 234864,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960921.496, "dur": 2.937, + "args": { + "External id": 234865,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960921.863, "dur": 2.407, + "args": { + "External id": 234866,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960924.683, "dur": 1.451, + "args": { + "External id": 234867,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960925.485, "dur": 0.576, + "args": { + "External id": 234868,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960926.389, "dur": 1.302, + "args": { + "External id": 234869,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960926.876, "dur": 0.742, + "args": { + "External id": 234870,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960928.130, "dur": 3.615, + "args": { + "External id": 234871,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960930.591, "dur": 1.087, + "args": { + "External id": 234872,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960932.011, "dur": 0.914, + "args": { + "External id": 234873,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960932.405, "dur": 0.458, + "args": { + "External id": 234874,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960933.196, "dur": 1.010, + "args": { + "External id": 234875,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960933.550, "dur": 0.584, + "args": { + "External id": 234876,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960934.687, "dur": 2.764, + "args": { + "External id": 234877,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960936.971, "dur": 0.418, + "args": { + "External id": 234878,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960937.697, "dur": 1.034, + "args": { + "External id": 234879,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960938.064, "dur": 0.599, + "args": { + "External id": 234880,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960938.987, "dur": 2.713, + "args": { + "External id": 234881,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960939.367, "dur": 2.063, + "args": { + "External id": 234882,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960941.950, "dur": 1.611, + "args": { + "External id": 234883,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960942.587, "dur": 0.914, + "args": { + "External id": 234884,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960943.821, "dur": 1.652, + "args": { + "External id": 234885,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960944.242, "dur": 1.160, + "args": { + "External id": 234886,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960945.723, "dur": 4.060, + "args": { + "External id": 234887,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960948.863, "dur": 0.851, + "args": { + "External id": 234888,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960950.077, "dur": 1.489, + "args": { + "External id": 234889,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960950.563, "dur": 0.942, + "args": { + "External id": 234890,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960951.843, "dur": 1.095, + "args": { + "External id": 234891,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960952.225, "dur": 0.641, + "args": { + "External id": 234892,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960953.425, "dur": 4.652, + "args": { + "External id": 234893,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960957.384, "dur": 0.623, + "args": { + "External id": 234894,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960958.521, "dur": 1.221, + "args": { + "External id": 234895,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960958.930, "dur": 0.747, + "args": { + "External id": 234896,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960960.114, "dur": 2.526, + "args": { + "External id": 234897,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960960.611, "dur": 1.953, + "args": { + "External id": 234898,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960962.889, "dur": 1.956, + "args": { + "External id": 234899,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960963.750, "dur": 1.033, + "args": { + "External id": 234900,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960965.191, "dur": 1.686, + "args": { + "External id": 234901,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960965.661, "dur": 1.144, + "args": { + "External id": 234902,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960967.189, "dur": 3.279, + "args": { + "External id": 234903,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960969.984, "dur": 0.419, + "args": { + "External id": 234904,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960970.818, "dur": 1.283, + "args": { + "External id": 234905,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960971.398, "dur": 0.643, + "args": { + "External id": 234906,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960972.467, "dur": 1.672, + "args": { + "External id": 234907,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960972.907, "dur": 1.159, + "args": { + "External id": 234908,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960974.411, "dur": 3.365, + "args": { + "External id": 234909,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960977.163, "dur": 0.548, + "args": { + "External id": 234910,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960978.111, "dur": 1.356, + "args": { + "External id": 234911,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960978.775, "dur": 0.626, + "args": { + "External id": 234912,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960979.794, "dur": 2.897, + "args": { + "External id": 234913,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960980.443, "dur": 2.173, + "args": { + "External id": 234914,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960983.049, "dur": 1.342, + "args": { + "External id": 234915,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960983.639, "dur": 0.690, + "args": { + "External id": 234916,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960984.665, "dur": 1.311, + "args": { + "External id": 234917,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960985.109, "dur": 0.797, + "args": { + "External id": 234918,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960986.336, "dur": 3.226, + "args": { + "External id": 234919,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960988.581, "dur": 0.916, + "args": { + "External id": 234920,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960989.889, "dur": 0.925, + "args": { + "External id": 234921,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960990.331, "dur": 0.421, + "args": { + "External id": 234922,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960991.189, "dur": 1.281, + "args": { + "External id": 234923,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960991.734, "dur": 0.669, + "args": { + "External id": 234924,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960993.001, "dur": 2.849, + "args": { + "External id": 234925,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960995.187, "dur": 0.598, + "args": { + "External id": 234926,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960996.150, "dur": 1.052, + "args": { + "External id": 234927,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960996.574, "dur": 0.562, + "args": { + "External id": 234928,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115960997.495, "dur": 2.740, + "args": { + "External id": 234929,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115960997.983, "dur": 2.180, + "args": { + "External id": 234930,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961000.515, "dur": 1.403, + "args": { + "External id": 234931,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961000.925, "dur": 0.924, + "args": { + "External id": 234932,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961002.203, "dur": 1.544, + "args": { + "External id": 234933,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961002.622, "dur": 1.058, + "args": { + "External id": 234934,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961004.025, "dur": 2.968, + "args": { + "External id": 234935,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961006.365, "dur": 0.560, + "args": { + "External id": 234936,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961007.306, "dur": 1.118, + "args": { + "External id": 234937,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961007.757, "dur": 0.604, + "args": { + "External id": 234938,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961008.704, "dur": 1.221, + "args": { + "External id": 234939,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961009.223, "dur": 0.635, + "args": { + "External id": 234940,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961010.462, "dur": 3.258, + "args": { + "External id": 234941,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961012.958, "dur": 0.701, + "args": { + "External id": 234942,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961013.994, "dur": 1.082, + "args": { + "External id": 234943,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961014.456, "dur": 0.555, + "args": { + "External id": 234944,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961015.551, "dur": 2.560, + "args": { + "External id": 234945,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961015.994, "dur": 2.047, + "args": { + "External id": 234946,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961018.396, "dur": 0.799, + "args": { + "External id": 234947,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961018.860, "dur": 0.265, + "args": { + "External id": 234948,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961019.538, "dur": 1.424, + "args": { + "External id": 234949,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961020.171, "dur": 0.723, + "args": { + "External id": 234950,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961021.255, "dur": 2.598, + "args": { + "External id": 234951,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961023.406, "dur": 0.382, + "args": { + "External id": 234952,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961024.167, "dur": 1.179, + "args": { + "External id": 234953,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961024.677, "dur": 0.601, + "args": { + "External id": 234954,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961025.814, "dur": 1.040, + "args": { + "External id": 234955,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961026.240, "dur": 0.548, + "args": { + "External id": 234956,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961027.312, "dur": 3.322, + "args": { + "External id": 234957,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961029.919, "dur": 0.652, + "args": { + "External id": 234958,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961030.918, "dur": 1.292, + "args": { + "External id": 234959,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961031.342, "dur": 0.803, + "args": { + "External id": 234960,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961032.487, "dur": 2.965, + "args": { + "External id": 234961,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961032.900, "dur": 2.482, + "args": { + "External id": 234962,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961035.739, "dur": 0.748, + "args": { + "External id": 234963,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961036.154, "dur": 0.264, + "args": { + "External id": 234964,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961036.758, "dur": 1.329, + "args": { + "External id": 234965,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961037.160, "dur": 0.859, + "args": { + "External id": 234966,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961038.412, "dur": 2.869, + "args": { + "External id": 234967,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961040.888, "dur": 0.325, + "args": { + "External id": 234968,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961041.573, "dur": 0.958, + "args": { + "External id": 234969,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961041.998, "dur": 0.471, + "args": { + "External id": 234970,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961042.813, "dur": 1.173, + "args": { + "External id": 234971,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961043.232, "dur": 0.688, + "args": { + "External id": 234972,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961044.619, "dur": 3.722, + "args": { + "External id": 234973,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961047.161, "dur": 1.116, + "args": { + "External id": 234974,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961048.636, "dur": 1.160, + "args": { + "External id": 234975,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961049.055, "dur": 0.676, + "args": { + "External id": 234976,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961050.076, "dur": 2.797, + "args": { + "External id": 234977,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961050.491, "dur": 2.311, + "args": { + "External id": 234978,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961053.149, "dur": 1.383, + "args": { + "External id": 234979,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961053.557, "dur": 0.909, + "args": { + "External id": 234980,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961054.912, "dur": 1.082, + "args": { + "External id": 234981,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961055.318, "dur": 0.610, + "args": { + "External id": 234982,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961056.276, "dur": 3.546, + "args": { + "External id": 234983,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961058.755, "dur": 0.998, + "args": { + "External id": 234984,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961060.118, "dur": 1.090, + "args": { + "External id": 234985,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961060.538, "dur": 0.602, + "args": { + "External id": 234986,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961061.508, "dur": 1.308, + "args": { + "External id": 234987,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961061.949, "dur": 0.799, + "args": { + "External id": 234988,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961063.131, "dur": 3.591, + "args": { + "External id": 234989,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961065.700, "dur": 0.955, + "args": { + "External id": 234990,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961066.996, "dur": 1.261, + "args": { + "External id": 234991,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961067.470, "dur": 0.720, + "args": { + "External id": 234992,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961068.896, "dur": 2.619, + "args": { + "External id": 234993,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961069.323, "dur": 1.917, + "args": { + "External id": 234994,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961071.778, "dur": 1.291, + "args": { + "External id": 234995,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961072.189, "dur": 0.810, + "args": { + "External id": 234996,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961073.465, "dur": 1.264, + "args": { + "External id": 234997,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961073.974, "dur": 0.684, + "args": { + "External id": 234998,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961075.239, "dur": 3.552, + "args": { + "External id": 234999,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961077.933, "dur": 0.785, + "args": { + "External id": 235000,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961079.079, "dur": 1.347, + "args": { + "External id": 235001,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961079.525, "dur": 0.832, + "args": { + "External id": 235002,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961080.714, "dur": 1.209, + "args": { + "External id": 235003,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961081.138, "dur": 0.718, + "args": { + "External id": 235004,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961082.385, "dur": 3.099, + "args": { + "External id": 235005,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961084.600, "dur": 0.817, + "args": { + "External id": 235006,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961085.975, "dur": 1.074, + "args": { + "External id": 235007,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961086.380, "dur": 0.603, + "args": { + "External id": 235008,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961106.056, "dur": 3.613, + "args": { + "External id": 235009,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961107.346, "dur": 2.251, + "args": { + "External id": 235010,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961109.939, "dur": 1.344, + "args": { + "External id": 235011,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961110.376, "dur": 0.837, + "args": { + "External id": 235012,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961111.596, "dur": 1.315, + "args": { + "External id": 235013,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961112.017, "dur": 0.827, + "args": { + "External id": 235014,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961113.214, "dur": 2.836, + "args": { + "External id": 235015,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961115.503, "dur": 0.480, + "args": { + "External id": 235016,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961116.440, "dur": 1.075, + "args": { + "External id": 235017,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961116.991, "dur": 0.458, + "args": { + "External id": 235018,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961117.900, "dur": 1.202, + "args": { + "External id": 235019,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961118.473, "dur": 0.562, + "args": { + "External id": 235020,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961119.590, "dur": 2.734, + "args": { + "External id": 235021,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961121.876, "dur": 0.380, + "args": { + "External id": 235022,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961122.624, "dur": 1.078, + "args": { + "External id": 235023,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961123.096, "dur": 0.542, + "args": { + "External id": 235024,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961124.087, "dur": 3.290, + "args": { + "External id": 235025,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961125.216, "dur": 2.086, + "args": { + "External id": 235026,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961127.642, "dur": 1.544, + "args": { + "External id": 235027,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961128.438, "dur": 0.687, + "args": { + "External id": 235028,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961129.498, "dur": 2.025, + "args": { + "External id": 235029,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961130.249, "dur": 1.207, + "args": { + "External id": 235030,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961131.781, "dur": 3.382, + "args": { + "External id": 235031,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961134.430, "dur": 0.665, + "args": { + "External id": 235032,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961135.646, "dur": 1.721, + "args": { + "External id": 235033,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961136.762, "dur": 0.540, + "args": { + "External id": 235034,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961137.665, "dur": 7.227, + "args": { + "External id": 235035,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961141.196, "dur": 3.623, + "args": { + "External id": 235036,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961145.220, "dur": 1.250, + "args": { + "External id": 235037,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961145.919, "dur": 0.484, + "args": { + "External id": 235038,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961146.708, "dur": 1.570, + "args": { + "External id": 235039,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961147.370, "dur": 0.838, + "args": { + "External id": 235040,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961148.781, "dur": 4.111, + "args": { + "External id": 235041,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961152.245, "dur": 0.585, + "args": { + "External id": 235042,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961153.200, "dur": 1.194, + "args": { + "External id": 235043,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961153.842, "dur": 0.482, + "args": { + "External id": 235044,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961154.688, "dur": 1.559, + "args": { + "External id": 235045,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961155.459, "dur": 0.719, + "args": { + "External id": 235046,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961156.730, "dur": 2.951, + "args": { + "External id": 235047,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961158.986, "dur": 0.624, + "args": { + "External id": 235048,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961159.970, "dur": 2.047, + "args": { + "External id": 235049,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961160.908, "dur": 1.044, + "args": { + "External id": 235050,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961162.378, "dur": 2.990, + "args": { + "External id": 235051,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961163.112, "dur": 2.185, + "args": { + "External id": 235052,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961165.656, "dur": 1.453, + "args": { + "External id": 235053,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961166.339, "dur": 0.705, + "args": { + "External id": 235054,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961167.543, "dur": 1.484, + "args": { + "External id": 235055,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961168.202, "dur": 0.758, + "args": { + "External id": 235056,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961169.295, "dur": 3.525, + "args": { + "External id": 235057,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961172.045, "dur": 0.713, + "args": { + "External id": 235058,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 4183440, "tid": 4183440, + "ts": 667115961173.103, "dur": 1.723, + "args": { + "External id": 235059,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961173.763, "dur": 0.999, + "args": { + "External id": 235060,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 4183440, "tid": 4183440, + "ts": 667115961194.942, "dur": 103.012, + "args": { + "External id": 235061,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linalg_vector_norm", "pid": 4183440, "tid": 4183440, + "ts": 667115961382.188, "dur": 141.803, + "args": { + "External id": 235062,"Record function id": 0, "Concrete Inputs": ["", "2.", "", "False", ""], "Input type": ["float", "Scalar", "", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[219], [], [], [], []], "Ev Idx": 9253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linalg_vector_norm", "pid": 4183440, "tid": 4183440, + "ts": 667115961443.537, "dur": 44.799, + "args": { + "External id": 235063,"Record function id": 0, "Concrete Inputs": ["", "2.", "", "False", ""], "Input type": ["float", "Scalar", "", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[219], [], [], [], []], "Ev Idx": 9254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 4183440, "tid": 4183440, + "ts": 667115961457.160, "dur": 0.924, + "args": { + "External id": 235064,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Redistribute", "pid": 4183440, "tid": 4183440, + "ts": 667115961836.822, "dur": 905.874, + "args": { + "External id": 235065,"Sequence number": 2757964, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "False"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 4183440, "tid": 4183440, + "ts": 667115961890.073, "dur": 52.907, + "args": { + "External id": 235066,"Record function id": 0, "Concrete Inputs": ["", "2."], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115961895.388, "dur": 1.410, + "args": { + "External id": 235067,"Record function id": 0, "Concrete Inputs": ["", "2."], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115961899.590, "dur": 0.551, + "args": { + "External id": 235068,"Record function id": 0, "Concrete Inputs": ["", "6", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 9259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::all_reduce", "pid": 4183440, "tid": 4183440, + "ts": 667115961965.499, "dur": 418.210, + "args": { + "External id": 235069,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["float", "", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 9260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 4183440, "tid": 4183440, + "ts": 667115961969.330, "dur": 43.122, + "args": { + "External id": 235070,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 4183440, "tid": 4183440, + "ts": 667115961972.674, "dur": 8.429, + "args": { + "External id": 235071,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "0"], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115961976.612, "dur": 3.795, + "args": { + "External id": 235072,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 4183440, "tid": 4183440, + "ts": 667115961982.576, "dur": 29.272, + "args": { + "External id": 235073,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 9264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::allreduce_", "pid": 4183440, "tid": 4183440, + "ts": 667115962022.203, "dur": 358.198, + "args": { + "External id": 235074,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "-1"], "Input type": ["TensorList", "", "", "", "Scalar"], "Input Strides": [[[]], [], [], [], []], "Input Dims": [[[]], [], [], [], []], "Ev Idx": 9265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115962051.478, "dur": 322.758, + "args": { + "External id": 235075,"Record function id": 0, "Collective name": "allreduce", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[[]], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1, "Process Group Name": "0", "Input type": ["TensorList", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[[]], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9266, "In msg nelems": 1 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:all_reduce", "pid": 4183440, "tid": 4183440, + "ts": 667115962068.896, "dur": 299.964, + "args": { + "External id": 235076,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 4183440, "tid": 4183440, + "ts": 667115962441.950, "dur": 263.848, + "args": { + "External id": 235077,"Record function id": 0, "Concrete Inputs": ["", "0.5"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::wait_tensor", "pid": 4183440, "tid": 4183440, + "ts": 667115962555.497, "dur": 32.359, + "args": { + "External id": 235078,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 4183440, "tid": 4183440, + "ts": 667115962573.385, "dur": 5.028, + "args": { + "External id": 235079,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 9270, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 4183440, "tid": 4183440, + "ts": 667115962618.120, "dur": 79.707, + "args": { + "External id": 235080,"Record function id": 0, "Concrete Inputs": ["", "0.5"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115962621.353, "dur": 1.321, + "args": { + "External id": 235081,"Record function id": 0, "Concrete Inputs": ["", "0.5"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115962624.374, "dur": 0.627, + "args": { + "External id": 235082,"Record function id": 0, "Concrete Inputs": ["", "6", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 9273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_ToTorchTensor", "pid": 4183440, "tid": 4183440, + "ts": 667115962758.807, "dur": 33.776, + "args": { + "External id": 235083,"Sequence number": 2757965, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 4183440, "tid": 4183440, + "ts": 667115962776.750, "dur": 9.967, + "args": { + "External id": 235084,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 4183440, "tid": 4183440, + "ts": 667115962779.895, "dur": 6.514, + "args": { + "External id": 235085,"Record function id": 0, "Concrete Inputs": ["", "[]"], "Input type": ["float", "ScalarList"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 4183440, "tid": 4183440, + "ts": 667115963141.981, "dur": 35.559, + "args": { + "External id": 235086,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "double", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 9277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reciprocal", "pid": 4183440, "tid": 4183440, + "ts": 667115963187.909, "dur": 22.667, + "args": { + "External id": 235087,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mul", "pid": 4183440, "tid": 4183440, + "ts": 667115963217.886, "dur": 33.581, + "args": { + "External id": 235088,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "double"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clamp", "pid": 4183440, "tid": 4183440, + "ts": 667115963266.657, "dur": 25.380, + "args": { + "External id": 235089,"Record function id": 0, "Concrete Inputs": ["", "", "1."], "Input type": ["float", "", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 9280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115963271.868, "dur": 0.807, + "args": { + "External id": 235090,"Record function id": 0, "Concrete Inputs": ["", "6", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 9281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 4183440, "tid": 4183440, + "ts": 667115963309.379, "dur": 0.337, + "args": { + "External id": 235091,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 9282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_mul_", "pid": 4183440, "tid": 4183440, + "ts": 667115963396.224, "dur": 531.373, + "args": { + "External id": 235092,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["TensorList", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_mul_", "pid": 4183440, "tid": 4183440, + "ts": 667115963838.590, "dur": 62.370, + "args": { + "External id": 235093,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["TensorList", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::isnan", "pid": 4183440, "tid": 4183440, + "ts": 667115963965.987, "dur": 24.920, + "args": { + "External id": 235094,"Sequence number": 2757966, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 4183440, "tid": 4183440, + "ts": 667115963969.386, "dur": 21.029, + "args": { + "External id": 235095,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 4183440, "tid": 4183440, + "ts": 667115963994.117, "dur": 467.951, + "args": { + "External id": 235096,"Sequence number": 2757966, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 4183440, "tid": 4183440, + "ts": 667115963995.740, "dur": 466.115, + "args": { + "External id": 235097,"Sequence number": 2757966, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 4183440, "tid": 4183440, + "ts": 667115963997.566, "dur": 463.959, + "args": { + "External id": 235098,"Sequence number": 2757966, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::isinf", "pid": 4183440, "tid": 4183440, + "ts": 667115964467.123, "dur": 73.869, + "args": { + "External id": 235099,"Sequence number": 2757966, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115964470.215, "dur": 45.878, + "args": { + "External id": 235100,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 4183440, "tid": 4183440, + "ts": 667115964475.875, "dur": 2.521, + "args": { + "External id": 235101,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 4183440, "tid": 4183440, + "ts": 667115964480.116, "dur": 35.230, + "args": { + "External id": 235102,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], [1]], "Input Dims": [[], [0]], "Ev Idx": 9293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 4183440, "tid": 4183440, + "ts": 667115964484.779, "dur": 2.421, + "args": { + "External id": 235103,"Record function id": 0, "Concrete Inputs": ["", "[]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 4183440, "tid": 4183440, + "ts": 667115964518.346, "dur": 21.803, + "args": { + "External id": 235104,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 4183440, "tid": 4183440, + "ts": 667115964543.430, "dur": 36.571, + "args": { + "External id": 235105,"Sequence number": 2757966, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 4183440, "tid": 4183440, + "ts": 667115964544.332, "dur": 35.531, + "args": { + "External id": 235106,"Sequence number": 2757966, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 4183440, "tid": 4183440, + "ts": 667115964545.178, "dur": 34.325, + "args": { + "External id": 235107,"Sequence number": 2757966, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9298 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#OptimizersContainer.step", "pid": 4183440, "tid": 4183440, + "ts": 667115964608.486, "dur": 4300.111, + "args": { + "External id": 235108,"Record function id": 0, "Ev Idx": 9299 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#AdamW.step", "pid": 4183440, "tid": 4183440, + "ts": 667115964640.662, "dur": 4247.926, + "args": { + "External id": 235109,"Record function id": 0, "Ev Idx": 9300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_add_", "pid": 4183440, "tid": 4183440, + "ts": 667115965585.423, "dur": 222.101, + "args": { + "External id": 235110,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965602.230, "dur": 0.836, + "args": { + "External id": 235111,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965604.046, "dur": 0.085, + "args": { + "External id": 235112,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965604.637, "dur": 0.319, + "args": { + "External id": 235113,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965605.343, "dur": 0.086, + "args": { + "External id": 235114,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965605.860, "dur": 0.195, + "args": { + "External id": 235115,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965606.449, "dur": 0.081, + "args": { + "External id": 235116,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965607.110, "dur": 0.065, + "args": { + "External id": 235117,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965607.576, "dur": 0.074, + "args": { + "External id": 235118,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965608.017, "dur": 0.072, + "args": { + "External id": 235119,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965608.397, "dur": 0.298, + "args": { + "External id": 235120,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965609.150, "dur": 0.051, + "args": { + "External id": 235121,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965609.637, "dur": 0.069, + "args": { + "External id": 235122,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965610.094, "dur": 0.066, + "args": { + "External id": 235123,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965610.670, "dur": 0.066, + "args": { + "External id": 235124,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965611.102, "dur": 0.063, + "args": { + "External id": 235125,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965611.535, "dur": 0.060, + "args": { + "External id": 235126,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965612.009, "dur": 0.049, + "args": { + "External id": 235127,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965612.550, "dur": 0.058, + "args": { + "External id": 235128,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965612.946, "dur": 0.067, + "args": { + "External id": 235129,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965613.405, "dur": 0.214, + "args": { + "External id": 235130,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965613.982, "dur": 0.100, + "args": { + "External id": 235131,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965614.402, "dur": 0.308, + "args": { + "External id": 235132,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965615.085, "dur": 0.056, + "args": { + "External id": 235133,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965615.455, "dur": 0.182, + "args": { + "External id": 235134,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965616.001, "dur": 0.209, + "args": { + "External id": 235135,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965616.558, "dur": 0.058, + "args": { + "External id": 235136,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965616.920, "dur": 0.213, + "args": { + "External id": 235137,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965617.439, "dur": 0.083, + "args": { + "External id": 235138,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965617.799, "dur": 0.084, + "args": { + "External id": 235139,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965618.263, "dur": 0.215, + "args": { + "External id": 235140,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965618.834, "dur": 0.066, + "args": { + "External id": 235141,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965619.149, "dur": 0.067, + "args": { + "External id": 235142,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965619.575, "dur": 0.066, + "args": { + "External id": 235143,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965619.990, "dur": 0.065, + "args": { + "External id": 235144,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965620.467, "dur": 0.065, + "args": { + "External id": 235145,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965620.875, "dur": 0.065, + "args": { + "External id": 235146,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965621.432, "dur": 0.067, + "args": { + "External id": 235147,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965621.850, "dur": 0.067, + "args": { + "External id": 235148,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965622.464, "dur": 0.060, + "args": { + "External id": 235149,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965622.884, "dur": 0.064, + "args": { + "External id": 235150,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965623.301, "dur": 0.061, + "args": { + "External id": 235151,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965623.663, "dur": 0.065, + "args": { + "External id": 235152,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965624.015, "dur": 0.067, + "args": { + "External id": 235153,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965624.468, "dur": 0.065, + "args": { + "External id": 235154,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965624.908, "dur": 0.062, + "args": { + "External id": 235155,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965625.288, "dur": 0.067, + "args": { + "External id": 235156,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965625.603, "dur": 0.069, + "args": { + "External id": 235157,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965625.967, "dur": 0.065, + "args": { + "External id": 235158,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965626.447, "dur": 0.067, + "args": { + "External id": 235159,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965626.868, "dur": 0.064, + "args": { + "External id": 235160,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965627.308, "dur": 0.064, + "args": { + "External id": 235161,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965627.631, "dur": 0.067, + "args": { + "External id": 235162,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965628.072, "dur": 0.063, + "args": { + "External id": 235163,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965628.541, "dur": 0.053, + "args": { + "External id": 235164,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965628.923, "dur": 0.067, + "args": { + "External id": 235165,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965629.381, "dur": 0.067, + "args": { + "External id": 235166,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965629.836, "dur": 0.063, + "args": { + "External id": 235167,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965630.293, "dur": 0.060, + "args": { + "External id": 235168,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965630.721, "dur": 0.063, + "args": { + "External id": 235169,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965631.188, "dur": 0.066, + "args": { + "External id": 235170,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965631.590, "dur": 0.065, + "args": { + "External id": 235171,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965631.933, "dur": 0.068, + "args": { + "External id": 235172,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965632.268, "dur": 0.062, + "args": { + "External id": 235173,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965632.695, "dur": 0.067, + "args": { + "External id": 235174,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965633.117, "dur": 0.068, + "args": { + "External id": 235175,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965633.554, "dur": 0.063, + "args": { + "External id": 235176,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965633.996, "dur": 0.064, + "args": { + "External id": 235177,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965634.398, "dur": 0.065, + "args": { + "External id": 235178,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965634.839, "dur": 0.084, + "args": { + "External id": 235179,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965635.272, "dur": 0.069, + "args": { + "External id": 235180,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965635.767, "dur": 0.059, + "args": { + "External id": 235181,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965636.180, "dur": 0.064, + "args": { + "External id": 235182,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965636.640, "dur": 0.062, + "args": { + "External id": 235183,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965637.056, "dur": 0.067, + "args": { + "External id": 235184,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965637.456, "dur": 0.065, + "args": { + "External id": 235185,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965637.868, "dur": 0.065, + "args": { + "External id": 235186,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965638.301, "dur": 0.064, + "args": { + "External id": 235187,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965638.717, "dur": 0.065, + "args": { + "External id": 235188,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965639.144, "dur": 0.059, + "args": { + "External id": 235189,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965639.599, "dur": 0.060, + "args": { + "External id": 235190,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965640.055, "dur": 0.065, + "args": { + "External id": 235191,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965640.500, "dur": 0.063, + "args": { + "External id": 235192,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965640.928, "dur": 0.062, + "args": { + "External id": 235193,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965641.368, "dur": 0.060, + "args": { + "External id": 235194,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965641.799, "dur": 0.064, + "args": { + "External id": 235195,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965642.374, "dur": 0.052, + "args": { + "External id": 235196,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965642.808, "dur": 0.065, + "args": { + "External id": 235197,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965643.390, "dur": 0.064, + "args": { + "External id": 235198,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965643.796, "dur": 0.065, + "args": { + "External id": 235199,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965644.176, "dur": 0.068, + "args": { + "External id": 235200,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965644.643, "dur": 0.065, + "args": { + "External id": 235201,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965645.006, "dur": 0.064, + "args": { + "External id": 235202,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965645.347, "dur": 0.073, + "args": { + "External id": 235203,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965645.717, "dur": 0.070, + "args": { + "External id": 235204,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965646.124, "dur": 0.066, + "args": { + "External id": 235205,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965646.481, "dur": 0.066, + "args": { + "External id": 235206,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965646.939, "dur": 0.067, + "args": { + "External id": 235207,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965647.273, "dur": 0.060, + "args": { + "External id": 235208,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965647.686, "dur": 0.062, + "args": { + "External id": 235209,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965648.114, "dur": 0.066, + "args": { + "External id": 235210,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965648.465, "dur": 0.200, + "args": { + "External id": 235211,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965649.420, "dur": 0.177, + "args": { + "External id": 235212,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965649.967, "dur": 0.055, + "args": { + "External id": 235213,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965650.377, "dur": 0.240, + "args": { + "External id": 235214,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965650.908, "dur": 0.062, + "args": { + "External id": 235215,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965651.375, "dur": 0.066, + "args": { + "External id": 235216,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965651.790, "dur": 0.063, + "args": { + "External id": 235217,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965679.965, "dur": 0.272, + "args": { + "External id": 235218,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965680.985, "dur": 0.206, + "args": { + "External id": 235219,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965681.597, "dur": 0.082, + "args": { + "External id": 235220,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965682.085, "dur": 0.067, + "args": { + "External id": 235221,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965682.528, "dur": 0.061, + "args": { + "External id": 235222,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965682.991, "dur": 0.054, + "args": { + "External id": 235223,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965683.446, "dur": 0.086, + "args": { + "External id": 235224,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965683.923, "dur": 0.060, + "args": { + "External id": 235225,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965684.350, "dur": 0.065, + "args": { + "External id": 235226,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965684.858, "dur": 0.060, + "args": { + "External id": 235227,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965685.292, "dur": 0.061, + "args": { + "External id": 235228,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965685.842, "dur": 0.066, + "args": { + "External id": 235229,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965686.315, "dur": 0.057, + "args": { + "External id": 235230,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965686.809, "dur": 0.059, + "args": { + "External id": 235231,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965687.231, "dur": 0.067, + "args": { + "External id": 235232,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965687.728, "dur": 0.061, + "args": { + "External id": 235233,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965688.201, "dur": 0.061, + "args": { + "External id": 235234,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965688.605, "dur": 0.060, + "args": { + "External id": 235235,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965689.027, "dur": 0.063, + "args": { + "External id": 235236,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965689.469, "dur": 0.056, + "args": { + "External id": 235237,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965689.865, "dur": 0.060, + "args": { + "External id": 235238,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965690.327, "dur": 0.065, + "args": { + "External id": 235239,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965690.672, "dur": 0.065, + "args": { + "External id": 235240,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965691.023, "dur": 0.050, + "args": { + "External id": 235241,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965691.421, "dur": 0.060, + "args": { + "External id": 235242,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965691.914, "dur": 0.060, + "args": { + "External id": 235243,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965692.444, "dur": 0.050, + "args": { + "External id": 235244,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965692.817, "dur": 0.048, + "args": { + "External id": 235245,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965693.236, "dur": 0.056, + "args": { + "External id": 235246,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965693.557, "dur": 0.056, + "args": { + "External id": 235247,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965693.928, "dur": 0.054, + "args": { + "External id": 235248,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965694.298, "dur": 0.054, + "args": { + "External id": 235249,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965694.759, "dur": 0.055, + "args": { + "External id": 235250,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965695.116, "dur": 0.054, + "args": { + "External id": 235251,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965695.698, "dur": 0.053, + "args": { + "External id": 235252,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965696.121, "dur": 0.055, + "args": { + "External id": 235253,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965696.588, "dur": 0.061, + "args": { + "External id": 235254,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965697.023, "dur": 0.062, + "args": { + "External id": 235255,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965697.474, "dur": 0.059, + "args": { + "External id": 235256,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965697.902, "dur": 0.060, + "args": { + "External id": 235257,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965698.354, "dur": 0.052, + "args": { + "External id": 235258,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965698.755, "dur": 0.063, + "args": { + "External id": 235259,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965699.136, "dur": 0.058, + "args": { + "External id": 235260,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965699.614, "dur": 0.051, + "args": { + "External id": 235261,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965700.017, "dur": 0.061, + "args": { + "External id": 235262,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965700.364, "dur": 0.069, + "args": { + "External id": 235263,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965700.744, "dur": 0.065, + "args": { + "External id": 235264,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965701.150, "dur": 0.061, + "args": { + "External id": 235265,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965701.545, "dur": 0.071, + "args": { + "External id": 235266,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965701.933, "dur": 0.064, + "args": { + "External id": 235267,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965702.343, "dur": 0.065, + "args": { + "External id": 235268,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965702.794, "dur": 0.065, + "args": { + "External id": 235269,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965703.241, "dur": 0.063, + "args": { + "External id": 235270,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965703.697, "dur": 0.061, + "args": { + "External id": 235271,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965704.114, "dur": 0.063, + "args": { + "External id": 235272,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965704.440, "dur": 0.066, + "args": { + "External id": 235273,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965704.844, "dur": 0.066, + "args": { + "External id": 235274,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965705.205, "dur": 0.067, + "args": { + "External id": 235275,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965705.545, "dur": 0.065, + "args": { + "External id": 235276,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965705.876, "dur": 0.061, + "args": { + "External id": 235277,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965706.230, "dur": 0.064, + "args": { + "External id": 235278,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965706.565, "dur": 0.063, + "args": { + "External id": 235279,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965706.930, "dur": 0.050, + "args": { + "External id": 235280,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965707.748, "dur": 0.057, + "args": { + "External id": 235281,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965708.165, "dur": 0.203, + "args": { + "External id": 235282,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965708.804, "dur": 0.088, + "args": { + "External id": 235283,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965709.143, "dur": 0.050, + "args": { + "External id": 235284,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965709.981, "dur": 0.064, + "args": { + "External id": 235285,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965710.297, "dur": 0.055, + "args": { + "External id": 235286,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965710.926, "dur": 0.065, + "args": { + "External id": 235287,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965711.243, "dur": 0.055, + "args": { + "External id": 235288,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965711.795, "dur": 0.189, + "args": { + "External id": 235289,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965712.231, "dur": 0.217, + "args": { + "External id": 235290,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965712.974, "dur": 0.095, + "args": { + "External id": 235291,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965713.437, "dur": 0.231, + "args": { + "External id": 235292,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965714.293, "dur": 0.064, + "args": { + "External id": 235293,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965714.778, "dur": 0.052, + "args": { + "External id": 235294,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965715.292, "dur": 0.063, + "args": { + "External id": 235295,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965715.700, "dur": 0.062, + "args": { + "External id": 235296,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965716.404, "dur": 0.065, + "args": { + "External id": 235297,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965716.829, "dur": 0.060, + "args": { + "External id": 235298,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965717.370, "dur": 0.062, + "args": { + "External id": 235299,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965717.821, "dur": 0.064, + "args": { + "External id": 235300,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965718.606, "dur": 0.064, + "args": { + "External id": 235301,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965718.919, "dur": 0.055, + "args": { + "External id": 235302,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965719.658, "dur": 0.063, + "args": { + "External id": 235303,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965719.972, "dur": 0.051, + "args": { + "External id": 235304,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965720.548, "dur": 0.062, + "args": { + "External id": 235305,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965720.861, "dur": 0.055, + "args": { + "External id": 235306,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965721.574, "dur": 0.061, + "args": { + "External id": 235307,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965721.883, "dur": 0.051, + "args": { + "External id": 235308,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965722.420, "dur": 0.061, + "args": { + "External id": 235309,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965722.743, "dur": 0.049, + "args": { + "External id": 235310,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965723.481, "dur": 0.067, + "args": { + "External id": 235311,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965723.818, "dur": 0.050, + "args": { + "External id": 235312,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965724.360, "dur": 0.063, + "args": { + "External id": 235313,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965724.668, "dur": 0.047, + "args": { + "External id": 235314,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965725.397, "dur": 0.063, + "args": { + "External id": 235315,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965725.721, "dur": 0.069, + "args": { + "External id": 235316,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965726.532, "dur": 0.061, + "args": { + "External id": 235317,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965726.841, "dur": 0.053, + "args": { + "External id": 235318,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965727.511, "dur": 0.064, + "args": { + "External id": 235319,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965727.822, "dur": 0.051, + "args": { + "External id": 235320,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965728.474, "dur": 0.065, + "args": { + "External id": 235321,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965728.784, "dur": 0.046, + "args": { + "External id": 235322,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965729.672, "dur": 0.066, + "args": { + "External id": 235323,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965729.981, "dur": 0.049, + "args": { + "External id": 235324,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965730.716, "dur": 0.064, + "args": { + "External id": 235325,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965731.025, "dur": 0.051, + "args": { + "External id": 235326,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965731.468, "dur": 0.068, + "args": { + "External id": 235327,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965731.779, "dur": 0.056, + "args": { + "External id": 235328,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 4183440, "tid": 4183440, + "ts": 667115965732.252, "dur": 0.065, + "args": { + "External id": 235329,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 9520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_fused_adamw_", "pid": 4183440, "tid": 4183440, + "ts": 667115966187.407, "dur": 2620.227, + "args": { + "External id": 235330,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "0.00029143140233429938", "0.90000000000000002", "0.94999999999999996", "0.10000000000000001", "1.0000000000000001e-15", "False", "False", "", ""], "Input type": ["TensorList", "TensorList", "TensorList", "TensorList", "TensorList", "TensorList", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_fused_adamw_", "pid": 4183440, "tid": 4183440, + "ts": 667115968426.420, "dur": 255.527, + "args": { + "External id": 235331,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "0.00029143140233429938", "0.90000000000000002", "0.94999999999999996", "0.10000000000000001", "1.0000000000000001e-15", "False", "False", "", ""], "Input type": ["TensorList", "TensorList", "TensorList", "TensorList", "TensorList", "TensorList", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9522 + } + }, + { + "name": "process_name", "ph": "M", "ts": 667115182761.034, "pid": 4183440, "tid": 0, + "args": { + "name": "python3.12" + } + }, + { + "name": "process_labels", "ph": "M", "ts": 667115182761.034, "pid": 4183440, "tid": 0, + "args": { + "labels": "CPU" + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 667115182761.034, "pid": 4183440, "tid": 0, + "args": { + "sort_index": 4183440 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 667115182761.034, "pid": 4183440, "tid": 4183440, + "args": { + "name": "thread 4183440 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 667115182761.034, "pid": 4183440, "tid": 4183440, + "args": { + "sort_index": 4183440 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 667115182761.034, "pid": 4183440, "tid": 31337, + "args": { + "name": "thread 31337 (pt_autograd_4)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 667115182761.034, "pid": 4183440, "tid": 31337, + "args": { + "sort_index": 31337 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 667115182761.034, "pid": 4183440, "tid": 31337, + "args": { + "name": "thread 31337 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 667115182761.034, "pid": 4183440, "tid": 31337, + "args": { + "sort_index": 31337 + } + }, + { + "ph": "X", "cat": "Trace", "ts": 667115182692.189, "dur": 786428.480, + "pid": "Spans", "tid": "PyTorch Profiler", + "name": "PyTorch Profiler (0)", + "args": { + "Op count": 0 + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 667115182692.189, + "pid": "Spans", "tid": 0, + "args": { + "sort_index": 536870912 + } + }, + { + "name": "Iteration Start: PyTorch Profiler", "ph": "i", "s": "g", + "pid": "Traces", "tid": "Trace PyTorch Profiler", "ts": 667115182692.189 + }, + { + "name": "Record Window End", "ph": "i", "s": "g", + "pid": "", "tid": "", "ts": 667116012619.989 + } + ], + "traceName": "exp/mtp.340M.batch16.seqlen4096.context4096.warmup1000.update1.steps100000.lr3e-4.cosine/profile_trace/iteration_12288/rank4_trace.json", + "displayTimeUnit": "ms", + "baseTimeNanoseconds": 1751410836000000000 +} \ No newline at end of file